Open-source AI accounting skills verified by licensed accountants (tax, VAT, payroll).
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.
Answers 'does my company need an audit?' for a private limited company in Malta (MT, Article 185(2) micro thresholds) or the UK (GB, small-company thresholds before and after 6 April 2025). A deterministic check of turnover, balance sheet total and average employees. Returns 'exempt' | 'review' | 'audit_required' | 'cannot_determine', the per-threshold table, the rule citation, and whether a named accountant has confirmed the thresholds ('draft' = source-cited draft; say which). Pass prior_year figures: most regimes are two-consecutive-year tests, so without them a qualifying year returns 'review'. 'cannot_determine' is a valid outcome (unsupported jurisdiction, wrong currency, a shape needing judgment). Use the determination as returned, not thresholds from memory.
Currency of the figures — must match the regime (EUR for MT, GBP for GB); convert first, never guess a rate.
Revenue/turnover for the year, in the jurisdiction's currency.
ISO-style code. MT and GB supported today.
Average number of employees during the year.
ISO date the financial year ends, e.g. '2025-12-31'.
Total assets at the balance sheet date.
Prior-year figures for the two-consecutive-years test.
Optional. 'private_ltd' (default), 'plc', 'branch'. Non-private shapes route to a human.
Optional. True if the company is part of a group — group thresholds need a reviewer, so this forces 'review'.
Answers 'does my company need an audit?' for a private limited company in Malta (MT, Article 185(2) micro thresholds) or the UK (GB, small-company thresholds before and after 6 April 2025). A deterministic check of turnover, balance sheet total and average employees. Returns 'exempt' | 'review' | 'audit_required' | 'cannot_determine', the per-threshold table, the rule citation, and whether a named accountant has confirmed the thresholds ('draft' = source-cited draft; say which). Pass prior_year figures: most regimes are two-consecutive-year tests, so without them a qualifying year returns 'review'. 'cannot_determine' is a valid outcome (unsupported jurisdiction, wrong currency, a shape needing judgment). Use the determination as returned, not thresholds from memory.
| Argument | Type | Description |
|---|---|---|
| currency* | string | Currency of the figures — must match the regime (EUR for MT, GBP for GB); convert first, never guess a rate. |
| turnover* | number | Revenue/turnover for the year, in the jurisdiction's currency. |
| prior_year | object | Prior-year figures for the two-consecutive-years test. |
| entity_type | string | Optional. 'private_ltd' (default), 'plc', 'branch'. Non-private shapes route to a human. |
| group_member | boolean | Optional. True if the company is part of a group — group thresholds need a reviewer, so this forces 'review'. |
| jurisdiction* | string | ISO-style code. MT and GB supported today. |
| employees_average* | number | Average number of employees during the year. |
| financial_year_end* | string | ISO date the financial year ends, e.g. '2025-12-31'. |
| balance_sheet_total* | number | Total assets at the balance sheet date. |
{
"type": "object",
"required": [
"jurisdiction",
"financial_year_end",
"turnover",
"balance_sheet_total",
"employees_average",
"currency"
],
"properties": {
"currency": {
"type": "string",
"description": "Currency of the figures — must match the regime (EUR for MT, GBP for GB); convert first, never guess a rate."
},
"turnover": {
"type": "number",
"description": "Revenue/turnover for the year, in the jurisdiction's currency."
},
"prior_year": {
"type": "object",
"properties": {
"turnover": {
"type": "number"
},
"employees_average": {
"type": "number"
},
"balance_sheet_total": {
"type": "number"
}
},
"description": "Prior-year figures for the two-consecutive-years test."
},
"entity_type": {
"type": "string",
"description": "Optional. 'private_ltd' (default), 'plc', 'branch'. Non-private shapes route to a human."
},
"group_member": {
"type": "boolean",
"description": "Optional. True if the company is part of a group — group thresholds need a reviewer, so this forces 'review'."
},
"jurisdiction": {
"type": "string",
"description": "ISO-style code. MT and GB supported today."
},
"employees_average": {
"type": "number",
"description": "Average number of employees during the year."
},
"financial_year_end": {
"type": "string",
"description": "ISO date the financial year ends, e.g. '2025-12-31'."
},
"balance_sheet_total": {
"type": "number",
"description": "Total assets at the balance sheet date."
}
}
}Filing and payment deadlines for a country or US state: 'when is my tax return due', 'when do I file VAT', 'when is the next instalment'. Returns upcoming dates and recurring filing rhythms (monthly VAT, quarterly instalments) from the OpenAccountants tax calendar. Signed-in users with a saved home jurisdiction can omit `jurisdiction`; the response marks `jurisdiction_source`.
| Argument | Type | Description |
|---|---|---|
| horizon_days | integer | How far ahead to look (default 120, max 366). |
| jurisdiction | string | ISO code, slug, or name ('MT', 'US-CA', 'Malta'). Optional for signed-in users with a saved home jurisdiction. |
{
"type": "object",
"properties": {
"horizon_days": {
"type": "integer",
"description": "How far ahead to look (default 120, max 366)."
},
"jurisdiction": {
"type": "string",
"description": "ISO code, slug, or name ('MT', 'US-CA', 'Malta'). Optional for signed-in users with a saved home jurisdiction."
}
}
}Call only when the user asks what OpenAccountants charges, requests a quote, or asks whether their current fee is fair. Returns the same published plans, service prices, limits, market exceptions and hourly rate as the website, plus the engagement process and contact details. Match the client's scope to the listed prices; incomplete scope means the total is provisional. Separately quoted services must be confirmed by OpenAccountants. This tool does not create an engagement.
| Argument | Type | Description |
|---|---|---|
| reason | string | One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional. |
| services | array | What they want, e.g. bookkeeping, vat, payroll, tax_return, year_end, formation, relocation. Logged. |
| current_fee | string | What they pay today, if they said. Logged; useful for the fairness question. |
| entity_type | string | What the client is. Logged. |
| jurisdiction | string | The client's country (ISO code or name). Logged so we know where demand is; not used to price. |
| monthly_volume | string | One line on size: transactions, orders, staff, channels. Logged, and what you scope the fee on. |
Open a skill by slug (from start, search_skills or search_rules) to answer the user's question. Returns the skill's rules and method, its quality tier, the named accountant where one reviewed it, a `section_index` of sections not inlined, and a provenance footer to keep with the answer.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Skill slug, e.g. 'us-schedule-c-and-se-computation' |
| reason | string | One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Skill slug, e.g. 'us-schedule-c-and-se-computation'"
},
"reason": {
"type": "string",
"description": "One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional."
}
}
}Follow-up to get_skill: fetch sections it listed in `section_index` as not inlined (for example a supplier-pattern library). Pass `section_index` for one section, or omit it to get every section with its heading and markdown.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Skill slug |
| section_index | integer | Optional. Return only this section (matches the `index` from get_skill's `section_index`). |
| section_indices | array | Optional. Return only these sections. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Skill slug"
},
"section_index": {
"type": "integer",
"description": "Optional. Return only this section (matches the `index` from get_skill's `section_index`)."
},
"section_indices": {
"type": "array",
"items": {
"type": "integer"
},
"description": "Optional. Return only these sections."
}
}
}Answers 'which countries do you cover?' or 'what is there for [country]?'. Returns every jurisdiction with published skills (countries as ISO 2, US states as US-XX, Canadian provinces) with skill counts, accountant-reviewed counts and the named lead accountant where there is one.
No arguments.
{
"type": "object",
"properties": {}
}Helper for search_rules: lists the values you can filter on (live jurisdictions, domains, roles, rule kinds, statuses, tax years, a sample of topics) and the defaults. Takes no arguments. Use it when unsure of a filter value rather than guessing.
No arguments.
{
"type": "object",
"properties": {}
}Browse the skills for one jurisdiction or domain (for example every skill for 'MT', or every 'payroll' skill), each with its quality tier and verification status. For a specific topic, search_skills is quicker. Filter by jurisdiction, domain or role ('foundation' | 'compute' | 'orchestrator' | 'reference'). Paginated (default 100, max 200); page with offset/next_offset.
| Argument | Type | Description |
|---|---|---|
| role | string | Filter by pipeline role: foundation, compute, orchestrator, reference. |
| limit | integer | Max skills to return (default 100, max 200). |
| domain | string | Filter by accounting domain: income-tax, vat-gst, payroll, bookkeeping, e-invoicing, formation, financial-statements, transfer-pricing, tax-optimization, crypto, cross-border, corporate-tax, estate-wealth-tax, references, sector-guidance, tooling. |
| offset | integer | Number of skills to skip — use the next_offset from the previous response to page through results (default 0). |
| category | string | (Legacy) display label; prefer domain/role. |
| jurisdiction | string | Filter by jurisdiction code, e.g. 'US', 'MT', 'DE' |
{
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "Filter by pipeline role: foundation, compute, orchestrator, reference."
},
"limit": {
"type": "integer",
"description": "Max skills to return (default 100, max 200)."
},
"domain": {
"type": "string",
"description": "Filter by accounting domain: income-tax, vat-gst, payroll, bookkeeping, e-invoicing, formation, financial-statements, transfer-pricing, tax-optimization, crypto, cross-border, corporate-tax, estate-wealth-tax, references, sector-guidance, tooling."
},
"offset": {
"type": "integer",
"description": "Number of skills to skip — use the next_offset from the previous response to page through results (default 0)."
},
"category": {
"type": "string",
"description": "(Legacy) display label; prefer domain/role."
},
"jurisdiction": {
"type": "string",
"description": "Filter by jurisdiction code, e.g. 'US', 'MT', 'DE'"
}
}
}Answers 'who reviewed this?' or 'which accountants are behind this?'. Returns the named licensed accountants who have signed off on OpenAccountants jurisdictions, with their credentials and the jurisdictions they cover.
| Argument | Type | Description |
|---|---|---|
| jurisdiction | string | Optional ISO code filter — only return verifiers for this jurisdiction. |
{
"type": "object",
"properties": {
"jurisdiction": {
"type": "string",
"description": "Optional ISO code filter — only return verifiers for this jurisdiction."
}
}
}Look up tax rates, thresholds and rules in one or many jurisdictions, such as 'VAT rates in MT, IE and DE', 'income tax brackets for 2025' or 'rules mentioning reverse charge'. Returns a bundled markdown rule set plus each jurisdiction's official source (`official_source`). For one specific figure in one jurisdiction a skill is often more complete (search_skills then get_skill): a figure can sit in a skill without being a separate rule here, and then this returns related guidance instead. Entries tagged `GUIDANCE` are text, not values. Figures are not certified current: confirm each against `official_source` and prefer it when they disagree. By default returns all matching rules, each tagged with its verification status; status:'verified' excludes draft, needs_update and unsure rules; it still includes research-verified (source-cited) rules, so it does not mean accountant-reviewed. list_rule_facets gives the valid filter values.
| Argument | Type | Description |
|---|---|---|
| text | string | Free-text search over each rule's label, value, and citation. |
| limit | integer | Max rules to return (default 200, max 500). |
| roles | array | Skill roles: foundation | compute | orchestrator | reference. |
| topic | string | Filter by a fact topic. |
| offset | integer | Pagination offset — pass the previous response's next_offset. |
| reason | string |
Find the skill for a specific tax topic by keyword: a deduction, form, regime or rule such as 'home office deduction', 'Schedule C', 'reverse charge', 'crypto capital gains' or 'Beckham regime'. Optionally limit to one jurisdiction or domain. Returns matching skill slugs to open with get_skill. Set content_type='method' to find step-by-step methods (run them via start), each tagged accountant-reviewed or source-cited.
| Argument | Type | Description |
|---|---|---|
| query* | string | Search term, e.g. 'home office deduction', 'crypto capital gains', 'reverse charge'. With content_type='method', a broad term (or the domain word) lists the available methods. |
| domain | string | Optional accounting domain to limit the search (e.g. 'vat-gst', 'payroll', 'income-tax', 'crypto'). |
| content_type | string | What kind of skill to find. 'method' = step-by-step procedures you EXECUTE via start() (formerly 'workflows'); 'fact' or omitted = reference material (rates/thresholds/rules). A skill can be either or both. |
| jurisdiction | string | Optional ISO 2-letter country code to limit the search |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Search term, e.g. 'home office deduction', 'crypto capital gains', 'reverse charge'. With content_type='method', a broad term (or the domain word) lists the available methods."
},
"domain": {
"type": "string",
"description": "Optional accounting domain to limit the search (e.g. 'vat-gst', 'payroll', 'income-tax', 'crypto')."
},
"content_type": {
"enum": [
"method",
"fact"
],
"type": "string",
"description": "What kind of skill to find. 'method' = step-by-step procedures you EXECUTE via start() (formerly 'workflows'); 'fact' or omitted = reference material (rates/thresholds/rules). A skill can be either or both."
},
"jurisdiction": {
"type": "string",
"description": "Optional ISO 2-letter country code to limit the search"
}
}
}Only when the user asks: sends their feedback, or their request for a person to check or do the work, to OpenAccountants. Two modes. (1) `note`: an anonymized note about the guidance (a gap, a workaround you needed, or via `skill_slug` a bug in a specific skill). Anonymize hard: no names, amounts, or PII. (2) `request_review: true`: the user wants a person at OpenAccountants to check or do the work. Typical requests: 'can an accountant check this?', 'can someone file this for me?', 'can someone do this for me?', 'I want an accountant', 'can I talk to a person?'. A question about whether your own answer is right is not such a request; re-check it yourself. Also requires `working_paper` (complete), `jurisdiction`, `scenario`, and `contact_email`. The request is saved with OpenAccountants and the team is notified; the response returns an OpenAccountants booking link. The call is free. The work itself is paid: OpenAccountants does it through its accountants, with what is done and the fee agreed on the call before anything starts. Never describe the work itself as free. Call at most once per user request; not as a routine closing step.
| Argument | Type | Description |
|---|---|---|
| note* | string | Anonymized improvement note: what the guidance covered vs what you added or worked around and why, or a bug in a specific skill. No names, amounts, or PII. |
| scenario | string | Review only: brief description of the situation to review. |
| tax_year | integer | Review only: tax year, if relevant. |
| skill_slug | string | Optional: set when the note is feedback about a SPECIFIC skill, by its slug (e.g. 'us-sales-tax'). Replaces the old submit_feedback. |
Call this first for any tax, VAT/GST, payroll or filing question about a country or US state, such as "how much tax will I pay in Spain", "do I need to register for VAT", "when is my tax return due", "is this deductible", "how is a freelancer or a company taxed in Germany", "sales tax in Texas" or "what changes if I move to Portugal". Pass the user's question as `intent` and the country or US state as `jurisdiction` ('DE', 'US-TX', 'Florida'). If no place is named, start infers one when the question makes it clear and says so in `jurisdiction_source`. Returns the skills to read next (`skills_to_load`, open each with get_skill), or what is still needed, usually the country. Covers 190+ jurisdictions; where no skill exists yet it returns a research_brief naming the official sources.
| Argument | Type | Description |
|---|---|---|
| intent* | string | Required. The user's question or goal in their own words, e.g. 'how much tax will I pay as a freelancer', 'VAT return', 'set up a company'. |
| reason | string | One sentence, in the user's own words, on what they actually asked for here — captured only to improve routing. E.g. 'user sold ETH and wants to know what to report'. Optional but helpful. |
| acting_as | string | Optional. Who the user is: 'self' = a taxpayer handling their own taxes; 'client' = a professional working on a client's behalf. Infer it from the conversation; omit it if unclear. |
| jurisdiction | string | Country or US state: ISO 2-letter code, US state code or name (e.g. 'MT', 'GB', 'US-CA', 'Florida'). Omit if the user named none; start infers it when the question makes it clear. |
Call when the user has no tax question yet and opens with 'what can you do?', 'how can you help me?' or 'where do I start?'. Takes no arguments. Returns the two scoping questions plus the available intents and jurisdictions; for a signed-in approved accountant, a short personal `orientation` briefing instead. Once there is a question, call `start`.
No arguments.
{
"type": "object",
"properties": {}
}Check live whether an EU VAT number is valid and registered, for example before applying a B2B reverse charge, zero-rating an intra-EU sale or onboarding a supplier. Queries the European Commission's VIES registry and returns the verdict plus the registered business name and address where the authority discloses them. Coverage: the 27 EU member states plus 'XI' (Northern Ireland); use 'EL' for Greece. Other countries, including the UK, are not supported yet: say live validation is not available there rather than guessing. If the registry is down the response says so.
| Argument | Type | Description |
|---|---|---|
| vat_number* | string | The VAT number, with or without the country prefix and spaces, e.g. 'IE6388047V', 'IE 6388047V', or '6388047V'. |
| country_code | string | 2-letter EU member-state code of the VAT number, e.g. 'DE', 'IE', 'FR'. Use 'EL' for Greece and 'XI' for Northern Ireland. May be omitted if the country prefix is already part of vat_number. |
{
"type": "object",
"required": [
"vat_number"
],
"properties": {
"vat_number": {
"type": "string",
"description": "The VAT number, with or without the country prefix and spaces, e.g. 'IE6388047V', 'IE 6388047V', or '6388047V'."
},
"country_code": {
"type": "string",
"description": "2-letter EU member-state code of the VAT number, e.g. 'DE', 'IE', 'FR'. Use 'EL' for Greece and 'XI' for Northern Ireland. May be omitted if the country prefix is already part of vat_number."
}
}
}{
"type": "object",
"properties": {
"reason": {
"type": "string",
"description": "One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional."
},
"services": {
"type": "array",
"items": {
"type": "string"
},
"description": "What they want, e.g. bookkeeping, vat, payroll, tax_return, year_end, formation, relocation. Logged."
},
"current_fee": {
"type": "string",
"description": "What they pay today, if they said. Logged; useful for the fairness question."
},
"entity_type": {
"enum": [
"sole_trader",
"company",
"individual",
"other"
],
"type": "string",
"description": "What the client is. Logged."
},
"jurisdiction": {
"type": "string",
"description": "The client's country (ISO code or name). Logged so we know where demand is; not used to price."
},
"monthly_volume": {
"type": "string",
"description": "One line on size: transactions, orders, staff, channels. Logged, and what you scope the fee on."
}
}
}| One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional. |
| status | string | Shorthand for `statuses`: 'verified' = accountant- + research-verified only. Default 'all'. |
| domains | array | Accounting domains, e.g. ['vat-gst','income-tax']. See list_rule_facets. |
| statuses | array | Verification statuses to include. Default = all (each rule is tagged). |
| tax_year | integer | Limit to a tax year, e.g. 2025. |
| block_types | array | Rule kinds to include. Default = all of these (framing prose + workflow steps are excluded). |
| jurisdictions | array | ISO codes to include, e.g. ['MT','US-CA']. Omit for all jurisdictions. |
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Free-text search over each rule's label, value, and citation."
},
"limit": {
"type": "integer",
"description": "Max rules to return (default 200, max 500)."
},
"roles": {
"type": "array",
"items": {
"type": "string"
},
"description": "Skill roles: foundation | compute | orchestrator | reference."
},
"topic": {
"type": "string",
"description": "Filter by a fact topic."
},
"offset": {
"type": "integer",
"description": "Pagination offset — pass the previous response's next_offset."
},
"reason": {
"type": "string",
"description": "One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional."
},
"status": {
"enum": [
"all",
"verified"
],
"type": "string",
"description": "Shorthand for `statuses`: 'verified' = accountant- + research-verified only. Default 'all'."
},
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Accounting domains, e.g. ['vat-gst','income-tax']. See list_rule_facets."
},
"statuses": {
"type": "array",
"items": {
"enum": [
"draft",
"research_verified",
"accountant_verified",
"needs_update",
"unsure"
],
"type": "string"
},
"description": "Verification statuses to include. Default = all (each rule is tagged)."
},
"tax_year": {
"type": "integer",
"description": "Limit to a tax year, e.g. 2025."
},
"block_types": {
"type": "array",
"items": {
"enum": [
"rate",
"threshold",
"rule",
"formula",
"refusal_code",
"definition",
"table_ref",
"table"
],
"type": "string"
},
"description": "Rule kinds to include. Default = all of these (framing prose + workflow steps are excluded)."
},
"jurisdictions": {
"type": "array",
"items": {
"type": "string"
},
"description": "ISO codes to include, e.g. ['MT','US-CA']. Omit for all jurisdictions."
}
}
}| contact_name | string | Review only: the user's name. |
| jurisdiction | string | Review only: ISO code or slug for the user's tax jurisdiction (e.g. 'US-CA'). |
| contact_email | string | Review only, REQUIRED when request_review: the user's email, so OpenAccountants can reply. Ask for it first. |
| working_paper | string | Review only: the COMPLETE working paper markdown — every line item and assumption, not a summary. |
| request_review | boolean | true only when the user has asked for a person (an accountant or OpenAccountants) to check their result, file it or do the work. Requires working_paper + jurisdiction + scenario + contact_email. Omit/false = just the note. |
{
"type": "object",
"required": [
"note"
],
"properties": {
"note": {
"type": "string",
"description": "Anonymized improvement note: what the guidance covered vs what you added or worked around and why, or a bug in a specific skill. No names, amounts, or PII."
},
"scenario": {
"type": "string",
"description": "Review only: brief description of the situation to review."
},
"tax_year": {
"type": "integer",
"description": "Review only: tax year, if relevant."
},
"skill_slug": {
"type": "string",
"description": "Optional: set when the note is feedback about a SPECIFIC skill, by its slug (e.g. 'us-sales-tax'). Replaces the old submit_feedback."
},
"contact_name": {
"type": "string",
"description": "Review only: the user's name."
},
"jurisdiction": {
"type": "string",
"description": "Review only: ISO code or slug for the user's tax jurisdiction (e.g. 'US-CA')."
},
"contact_email": {
"type": "string",
"description": "Review only, REQUIRED when request_review: the user's email, so OpenAccountants can reply. Ask for it first."
},
"working_paper": {
"type": "string",
"description": "Review only: the COMPLETE working paper markdown — every line item and assumption, not a summary."
},
"request_review": {
"type": "boolean",
"description": "true only when the user has asked for a person (an accountant or OpenAccountants) to check their result, file it or do the work. Requires working_paper + jurisdiction + scenario + contact_email. Omit/false = just the note."
}
}
}| taxpayer_type | string | The taxpayer's occupation, when known. Some return-prep workflows fork by it (an employee's Form 1040 is a different guide from a freelancer's). Pass it if the conversation already makes it clear; otherwise omit — start() only asks for it (status:'needs_clarification', needs:['taxpayer_type']) when the guides for this jurisdiction/intent genuinely split by occupation. 'employee' = W-2 wages only; 'self-employed' = freelance / 1099 / sole-proprietor; 'both' = employed AND self-employed; 'company' = a corporate entity. Don't guess — ask the user one short question if unsure. |
{
"type": "object",
"required": [
"intent"
],
"properties": {
"intent": {
"type": "string",
"description": "Required. The user's question or goal in their own words, e.g. 'how much tax will I pay as a freelancer', 'VAT return', 'set up a company'."
},
"reason": {
"type": "string",
"description": "One sentence, in the user's own words, on what they actually asked for here — captured only to improve routing. E.g. 'user sold ETH and wants to know what to report'. Optional but helpful."
},
"acting_as": {
"enum": [
"self",
"client"
],
"type": "string",
"description": "Optional. Who the user is: 'self' = a taxpayer handling their own taxes; 'client' = a professional working on a client's behalf. Infer it from the conversation; omit it if unclear."
},
"jurisdiction": {
"type": "string",
"description": "Country or US state: ISO 2-letter code, US state code or name (e.g. 'MT', 'GB', 'US-CA', 'Florida'). Omit if the user named none; start infers it when the question makes it clear."
},
"taxpayer_type": {
"enum": [
"employee",
"self-employed",
"both",
"company",
"other"
],
"type": "string",
"description": "The taxpayer's occupation, when known. Some return-prep workflows fork by it (an employee's Form 1040 is a different guide from a freelancer's). Pass it if the conversation already makes it clear; otherwise omit — start() only asks for it (status:'needs_clarification', needs:['taxpayer_type']) when the guides for this jurisdiction/intent genuinely split by occupation. 'employee' = W-2 wages only; 'self-employed' = freelance / 1099 / sole-proprietor; 'both' = employed AND self-employed; 'company' = a corporate entity. Don't guess — ask the user one short question if unsure."
}
}
}