Server Quality Checklist

Tool Scores

• search_companyA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by stating 'Read-only' and specifying data sources (Polish court and statistical registers), which clarifies behavior beyond annotations.

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

  Conciseness5/5

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

  The description is concise: three sentences with no fluff. The purpose is front-loaded, and every sentence adds essential information.

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

  Completeness4/5

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

  Given the tool's simplicity (2 parameters, no output schema), the description adequately covers return fields and data sources. It is complete for its complexity, though an output schema could enhance completeness.

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

  Parameters3/5

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

  Schema coverage is 100% with descriptions for both parameters. The description adds only the 'fuzzy match' nuance for the query parameter, which is a small improvement over the schema.

  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?

  The description clearly states the tool searches Polish companies by name with fuzzy match, and lists the returned data (NIP, KRS, city, status, profile URL). It distinguishes from siblings like 'get_company' which is likely for specific company lookups.

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

  Usage Guidelines4/5

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

  The description explicitly says 'USE THIS when the user asks to find a Polish company, look up a firm by name, or get its NIP/KRS/REGON.' It provides clear context, but does not mention when not to use or alternatives.

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

• get_financialsA
  4.3/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds 'Read-only' confirming safety. Also specifies data source (RDF/KRS) and yearly frequency, which are behavioral traits beyond annotations. No contradictions.

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

  Conciseness5/5

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

  Two sentences with no wasted words. First sentence defines action and data source; second provides usage guidance and return value summary. Clearly front-loaded and efficient.

  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?

  Despite no output schema, the description lists the specific financial metrics returned (revenue, net profit, total assets, equity, liabilities) per year. Covers purpose, usage, and output adequately for a simple tool with one parameter.

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

  Parameters3/5

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

  Schema description coverage is 100%—the single parameter 'nip' is fully described with pattern and meaning. The description does not add extra parameter semantics beyond what the schema provides, so baseline of 3 is appropriate.

  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?

  Clearly states the tool gets yearly financial statements of a Polish company by NIP, from KRS. Lists specific data types returned (revenue, profit, assets). Unambiguous and distinguishes from siblings which handle different company data (vat, general info, search).

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

  Usage Guidelines4/5

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

  Explicitly says 'USE THIS when the user asks about revenue, profit, assets or financial results.' Provides clear context for when to use, though does not explicitly state when not to use or suggest alternatives. Given sibling tools, the purpose is well-differentiated.

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

• check_vat_whitelistA
  4.5/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, idempotentHint, destructiveHint, and openWorldHint. The description adds that it is a 'live query to the official KAS register' and describes the return values (VAT status and account-match result), providing context beyond annotations.

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

  Conciseness5/5

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

  Three sentences with no redundancy. Front-loaded with purpose, followed by usage guidance, then return info and nature. Every sentence adds value.

  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?

  For a tool with two parameters and no output schema, the description covers purpose, usage context, return values, and live query nature. Annotations handle safety profile. No gaps identified.

  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%, but the description adds functional meaning: it explains that the NIP is a Polish tax ID, that the account number is optional and for checking registration, and implies the optionality of the account parameter. This goes beyond the schema's basic type and pattern.

  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?

  The description clearly identifies the tool's function: checking a Polish company's VAT status in the official white list register and optionally verifying a bank account. It distinguishes from siblings by focusing on VAT compliance, which is not covered by get_company, get_financials, or search_company.

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

  Usage Guidelines4/5

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

  Explicitly states 'USE THIS before paying an invoice' and explains the tax consequence of paying over PLN 15,000 to an account not on the white list. This provides strong use-case guidance, though it does not explicitly mention when not to use it relative to siblings.

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

• get_companyA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint, idempotentHint, destructiveHint false. Description adds that data comes from public registers and is read-only, reinforcing safety. No contradictions.

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

  Conciseness5/5

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

  Two sentences: first states purpose and usage, second lists return data and sources. No fluff, well structured.

  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 single parameter, no output schema, and strong annotations, description fully covers what the tool does, what it returns, and data sources. Complete for agent invocation.

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

  Parameters3/5

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

  Schema coverage is 100% with regex and description. Description repeats '10-digit tax ID' but adds no new meaning beyond schema. Baseline 3 is appropriate.

  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?

  Title 'Get full company profile by NIP' and description clearly state verb (get) and resource (company profile) with identifier (NIP). Lists specific data returned, distinguishing it from siblings like search_company.

  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 says 'USE THIS when the user gives a NIP and wants company details...' and lists what it returns, implicitly excluding financial queries (get_financials) or search (search_company).

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