OpenAccountants

Look up tax rates and rules

search_rules

Read-onlyIdempotent

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.

Input Schema

Name	Required	Description
`text`	No	Free-text search over each rule's label, value, and citation.
`limit`	No	Max rules to return (default 200, max 500).
`roles`	No	Skill roles: foundation \| compute \| orchestrator \| reference.
`topic`	No	Filter by a fact topic.
`offset`	No	Pagination offset — pass the previous response's next_offset.
`reason`	No	One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional.
`status`	No	Shorthand for `statuses`: 'verified' = accountant- + research-verified only. Default 'all'.
`domains`	No	Accounting domains, e.g. ['vat-gst','income-tax']. See list_rule_facets.
`statuses`	No	Verification statuses to include. Default = all (each rule is tagged).
`tax_year`	No	Limit to a tax year, e.g. 2025.
`block_types`	No	Rule kinds to include. Default = all of these (framing prose + workflow steps are excluded).
`jurisdictions`	No	ISO codes to include, e.g. ['MT','US-CA']. Omit for all jurisdictions.

Output Schema

Name	Required	Description
`total`	No	Total matching rules (across all pages).
`markdown`	Yes	The bundled rule set as markdown — the user saves/runs this locally.
`truncated`	No
`fact_count`	Yes	Rules returned on this page.
`next_action`	No
`next_offset`	No
`jurisdictions`	No
`accountant_verified_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 13, 2026

addedInput schema / properties / reason

Added value: +{
+  "description": "One sentence on WHY you're making this call, in the user's terms (for routing analysis only). Optional.",
+  "type": "string"
+}

AddedJun 23, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (readOnly/idempotent/non-destructive), but the description adds substantial behavioral context beyond them: it returns a bundled markdown rule set plus official_source, GUIDANCE entries are text not values, figures are not certified current and should be confirmed against official_source, and the status:'verified' filter does NOT mean accountant-reviewed. These are non-obvious traits an agent would otherwise get wrong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: the core capability and examples come first, then caveats. Every sentence carries information (skill routing, GUIDANCE tagging, verification caveats), though the description is on the long side and the parenthetical routing guidance is packed tightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a 12-parameter tool with an output schema and full annotation coverage, the description closes the remaining gaps: what is returned, what verification status means, and the reliability caveat about figures. An agent has everything needed to call and interpret it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description earns extra credit by clarifying semantics the schema does not: status:'verified' includes research-verified rules and excludes draft/needs_update/unsure, and default behavior returns all matching rules tagged with verification status. This directly disambiguates the status/statuses pair.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (look up) and resource (tax rates, thresholds and rules) with concrete query examples in multiple jurisdictions. It also contrasts itself with search_skills/get_skill, so an agent can distinguish it from siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: 'For one specific figure in one jurisdiction a skill is often more complete (search_skills then get_skill)', explains why a figure may not appear here, and points to list_rule_facets for valid filter values. Both the when-to-use and the when-to-use-something-else cases are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All OpenAccountants tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.