Live lab grown diamond inventory, engagement ring settings, fine jewelry, and diamond buying guides.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Assemble a cart and get a Stripe-hosted checkout URL the customer opens to pay; no card data passes through the agent. Item ids come from the search tools (`diamond:<report>`, `setting:<slug>`, `jewelry:<slug>`); a complete ring is one setting plus one diamond. Needs the shipping address (prices tax and shipping into the link). Expires after 24 hours. No credential needed. Without a production credential this tool runs in the sandbox: the link is simulated and no Stripe session is created. Pass `env: "production"` when the customer actually wants to buy — that returns a live, payable link.
Items to buy; a complete ring is one setting plus one diamond
Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
Where the order ships; used to price tax and shipping into the link
sandbox returns a simulated link and creates no Stripe session; production mints a live, payable Stripe Checkout link. Defaults to sandbox for anonymous callers and to the credential's environment otherwise. A sandbox credential is always sandbox.
Buyer full name
Buyer email for the receipt; Stripe collects it on the payment page when omitted
Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Tool list last changed Oct 23, 2026.
Assemble a cart and get a Stripe-hosted checkout URL the customer opens to pay; no card data passes through the agent. Item ids come from the search tools (`diamond:<report>`, `setting:<slug>`, `jewelry:<slug>`); a complete ring is one setting plus one diamond. Needs the shipping address (prices tax and shipping into the link). Expires after 24 hours. No credential needed. Without a production credential this tool runs in the sandbox: the link is simulated and no Stripe session is created. Pass `env: "production"` when the customer actually wants to buy — that returns a live, payable link.
| Argument | Type | Description |
|---|---|---|
| env | string | sandbox returns a simulated link and creates no Stripe session; production mints a live, payable Stripe Checkout link. Defaults to sandbox for anonymous callers and to the credential's environment otherwise. A sandbox credential is always sandbox. |
| items* | array | Items to buy; a complete ring is one setting plus one diamond |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| buyer_name | string | Buyer full name |
| buyer_email | string | Buyer email for the receipt; Stripe collects it on the payment page when omitted |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
| shipping_address* | object | Where the order ships; used to price tax and shipping into the link |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"items",
"shipping_address",
"context",
"llm_model"
],
"properties": {
"env": {
"enum": [
"production",
"sandbox"
],
"type": "string",
"description": "sandbox returns a simulated link and creates no Stripe session; production mints a live, payable Stripe Checkout link. Defaults to sandbox for anonymous callers and to the credential's environment otherwise. A sandbox credential is always sandbox."
},
"items": {
"type": "array",
"items": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Catalog item id: `diamond:<report number>`, `setting:<slug>`, or `jewelry:<slug>` (from search_diamonds / search_engagement_rings / search_jewelry results)"
},
"quantity": {
"type": "integer",
"default": 1,
"maximum": 10,
"minimum": 1,
"description": "Quantity, 1-10 (diamonds are always 1)"
}
}
},
"maxItems": 20,
"minItems": 1,
"description": "Items to buy; a complete ring is one setting plus one diamond"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"buyer_name": {
"type": "string",
"description": "Buyer full name"
},
"buyer_email": {
"type": "string",
"description": "Buyer email for the receipt; Stripe collects it on the payment page when omitted"
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
},
"shipping_address": {
"type": "object",
"required": [
"line_one",
"city",
"state",
"postal_code",
"country"
],
"properties": {
"city": {
"type": "string",
"description": "City"
},
"name": {
"type": "string",
"description": "Recipient name"
},
"state": {
"type": "string",
"description": "State or region code, e.g. NY"
},
"country": {
"type": "string",
"description": "Two-letter country code, e.g. US"
},
"line_one": {
"type": "string",
"description": "Street address, line 1"
},
"line_two": {
"type": "string",
"description": "Street address, line 2"
},
"postal_code": {
"type": "string",
"description": "Postal code"
},
"phone_number": {
"type": "string",
"description": "Recipient phone number"
}
},
"description": "Where the order ships; used to price tax and shipping into the link"
}
}
}Contact details, showroom address and hours, how consultations work, and what Ada Diamonds sells. Use this to answer questions about the business rather than about a product.
| Argument | Type | Description |
|---|---|---|
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
| section | string | Which part to return as text: contact (phone, email, hours, website), showrooms (addresses and hours), consultations (how remote and in-person consultations work), or all (default). The structured result always carries every section. |
| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
Fetch the full markdown text of one Ada Diamonds knowledge base article by slug. Use search_knowledge_base first if you don't know the slug.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Article slug from search_knowledge_base, e.g. "cvd-lab-diamonds" or "lab-diamond-shapes-guide" |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
Submit a consultation request on the customer's behalf. Requires the `appointments:write` scope, which the customer grants through Ada's OAuth authorization flow — this tool cannot be used without their explicit approval.
| Argument | Type | Description |
|---|---|---|
| name | string | Customer's name |
| email* | string | Customer's email address; the jeweler replies here |
| phone | string | Customer's phone number, if they want a call |
| topic | string | What the consultation is about |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
| message | string | What the customer is looking for, in their words |
| llm_model* | string |
Search Ada Diamonds' live loose lab grown diamond inventory by shape, carat weight, price, color, clarity, and cut. Returns currently available stones with their grading report numbers and product URLs. Use this for any question about what diamond a budget can buy. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.
| Argument | Type | Description |
|---|---|---|
| cut | string | Cut grade: Ideal, Excellent, or Very Good |
| sort | string | Result order: price_asc (default relevance), price_desc, carat_asc, or carat_desc |
| color | string | Color grade, D (colorless) through K |
| limit | number | Maximum number of results to return, 1 to 50 (default 10) |
| shape | string | Cut shape: Round, Oval, Cushion, Emerald, Pear, Radiant, Asscher, Princess, or Marquise |
| clarity | string | Clarity grade: FL, IF, VVS1, VVS2, VS1, VS2, SI1, or SI2 |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
Search Ada Diamonds' engagement ring settings by center-stone shape, style, and setting price. Setting prices exclude the center diamond — pair with search_diamonds to quote a complete ring. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.
| Argument | Type | Description |
|---|---|---|
| q | string | Free text, e.g. "east west bezel"; typo tolerant, best match first |
| type | string | Setting type, e.g. Solitaire, Halo, Three Stone |
| limit | number | Maximum number of results to return, 1 to 50 (default 10) |
| shape | string | Center-stone shape the setting must accommodate, e.g. Oval |
| style | string | Design style, e.g. Petite Four Prong, Trellis, Bezel |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
Search Ada Diamonds' fine jewelry — wedding bands, earrings, necklaces, bracelets, and fashion rings — by category, type, diamond shape, and price. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.
| Argument | Type | Description |
|---|---|---|
| q | string | Free text, e.g. "east west bezel"; typo tolerant, best match first |
| type | string | Type, e.g. Wedding Bands, Earrings, Necklaces, Bracelets, Rings |
| limit | number | Maximum number of results to return, 1 to 50 (default 10) |
| shape | string | Diamond shape used in the piece, e.g. Round |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
| category | string | Category: Bridal or Fashion |
Search Ada Diamonds' published guides on lab grown diamonds — the 4Cs, CVD vs HPHT growth, shape guides, certification, and buying advice. Returns article summaries and markdown URLs. Use read_article to get an article's full text.
| Argument | Type | Description |
|---|---|---|
| limit | number | Maximum number of results to return, 1 to 25 (default 8) |
| query* | string | Topic to search for, matched against article titles, summaries, and slugs |
| context* | string | Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution." |
| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| conversation_id |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"properties": {
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"section": {
"enum": [
"all",
"contact",
"showrooms",
"consultations"
],
"type": "string",
"default": "all",
"description": "Which part to return as text: contact (phone, email, hours, website), showrooms (addresses and hours), consultations (how remote and in-person consultations work), or all (default). The structured result always carries every section."
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"slug",
"context",
"llm_model"
],
"properties": {
"slug": {
"type": "string",
"description": "Article slug from search_knowledge_base, e.g. \"cvd-lab-diamonds\" or \"lab-diamond-shapes-guide\""
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}| The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| budget_usd | number | Approximate budget in US dollars |
| product_url | string | URL of a specific diamond, setting, or piece they are interested in |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"email",
"context",
"llm_model"
],
"properties": {
"name": {
"type": "string",
"description": "Customer's name"
},
"email": {
"type": "string",
"description": "Customer's email address; the jeweler replies here"
},
"phone": {
"type": "string",
"description": "Customer's phone number, if they want a call"
},
"topic": {
"enum": [
"engagement_ring",
"loose_diamond",
"wedding_band",
"fine_jewelry",
"custom_design",
"other"
],
"type": "string",
"description": "What the consultation is about"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"message": {
"type": "string",
"description": "What the customer is looking for, in their words"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"budget_usd": {
"type": "number",
"description": "Approximate budget in US dollars"
},
"product_url": {
"type": "string",
"description": "URL of a specific diamond, setting, or piece they are interested in"
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| max_carat | number | Maximum carat weight, e.g. 2 |
| max_price | number | Maximum price of the loose stone in US dollars |
| min_carat | number | Minimum carat weight, e.g. 1 or 1.5 |
| min_price | number | Minimum price of the loose stone in US dollars |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"properties": {
"cut": {
"type": "string",
"description": "Cut grade: Ideal, Excellent, or Very Good"
},
"sort": {
"enum": [
"price_asc",
"price_desc",
"carat_asc",
"carat_desc"
],
"type": "string",
"description": "Result order: price_asc (default relevance), price_desc, carat_asc, or carat_desc"
},
"color": {
"type": "string",
"description": "Color grade, D (colorless) through K"
},
"limit": {
"type": "number",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of results to return, 1 to 50 (default 10)"
},
"shape": {
"type": "string",
"description": "Cut shape: Round, Oval, Cushion, Emerald, Pear, Radiant, Asscher, Princess, or Marquise"
},
"clarity": {
"type": "string",
"description": "Clarity grade: FL, IF, VVS1, VVS2, VS1, VS2, SI1, or SI2"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"max_carat": {
"type": "number",
"description": "Maximum carat weight, e.g. 2"
},
"max_price": {
"type": "number",
"description": "Maximum price of the loose stone in US dollars"
},
"min_carat": {
"type": "number",
"description": "Minimum carat weight, e.g. 1 or 1.5"
},
"min_price": {
"type": "number",
"description": "Minimum price of the loose stone in US dollars"
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| max_price | number | Maximum setting price in US dollars, excluding the center diamond |
| min_price | number | Minimum setting price in US dollars, excluding the center diamond |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"properties": {
"q": {
"type": "string",
"description": "Free text, e.g. \"east west bezel\"; typo tolerant, best match first"
},
"type": {
"type": "string",
"description": "Setting type, e.g. Solitaire, Halo, Three Stone"
},
"limit": {
"type": "number",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of results to return, 1 to 50 (default 10)"
},
"shape": {
"type": "string",
"description": "Center-stone shape the setting must accommodate, e.g. Oval"
},
"style": {
"type": "string",
"description": "Design style, e.g. Petite Four Prong, Trellis, Bezel"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"max_price": {
"type": "number",
"description": "Maximum setting price in US dollars, excluding the center diamond"
},
"min_price": {
"type": "number",
"description": "Minimum setting price in US dollars, excluding the center diamond"
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| max_price | number | Maximum price in US dollars |
| min_price | number | Minimum price in US dollars |
| conversation_id | string | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"properties": {
"q": {
"type": "string",
"description": "Free text, e.g. \"east west bezel\"; typo tolerant, best match first"
},
"type": {
"type": "string",
"description": "Type, e.g. Wedding Bands, Earrings, Necklaces, Bracelets, Rings"
},
"limit": {
"type": "number",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of results to return, 1 to 50 (default 10)"
},
"shape": {
"type": "string",
"description": "Diamond shape used in the piece, e.g. Round"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"category": {
"type": "string",
"description": "Category: Bridal or Fashion"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"max_price": {
"type": "number",
"description": "Maximum price in US dollars"
},
"min_price": {
"type": "number",
"description": "Minimum price in US dollars"
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}| string |
| Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query",
"context",
"llm_model"
],
"properties": {
"limit": {
"type": "number",
"default": 8,
"maximum": 25,
"minimum": 1,
"description": "Maximum number of results to return, 1 to 25 (default 8)"
},
"query": {
"type": "string",
"description": "Topic to search for, matched against article titles, summaries, and slugs"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
}
}