Server Quality Checklist

Tool Scores

• search_bank_accountA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnly and idempotent hints, but the description adds valuable behavior beyond that: it counts toward the 'search' method limit, lists specific error codes (invalid_bank_account, invalid_date, not_found), and explains the real-world tax/VAT consequences. This enriches the agent's understanding without contradicting annotations.

  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?

  The description is concise and front-loaded with the primary purpose, followed by a practical use case, a rate-limit note, and error list. It contains relevant information without excessive fluff, though slightly longer than necessary. Efficient but not as tight as the two-sentence ideal.

  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?

  Despite having no output schema, the description explains the search purpose, input format, rate-limit counting, and possible errors, providing a solid operational context. It does not detail the return structure or pagination, but given the tool's simplicity and strong annotations, it is sufficiently complete for an agent to invoke correctly.

  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?

  The schema covers 100% of parameters with clear descriptions (bank_account format, date default). The description's mention of '26 digits, NRB format, without PL' is nearly redundant with the schema's own parameter description. No additional semantics beyond what the schema already provides, so baseline 3 applies.

  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's function: 'Finds entity(ies) to which a given bank account is assigned' with specific format details. It distinguishes from sibling search tools by focusing on bank account numbers rather than NIP or REGON, making it unambiguous.

  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 provides a strong usage context: 'Useful when you have an account number from an invoice and want to check if it matches the white list BEFORE transfer.' It also warns about the 'search' method limit, but it does not explicitly exclude alternatives like 'check_nip_bank_account' or 'search_nip', so it lacks explicit when-not-to-use guidance.

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

• check_nip_bank_accountA
  4.4/5.0
  Behavior4/5

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

  Beyond annotations (readOnlyHint=true, idempotentHint=true), description adds error codes (invalid_nip, invalid_bank_account, etc.) and rate-limit context, plus clarifies it returns a binary TAK/NIE result.

  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 fluff; the error list is compact and the usage guidance is integrated into a single clause.

  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?

  For a simple boolean check tool, the description covers the return nature ('TAK/NIE'), identifies the appropriate use case, lists potential errors, and leverages annotations for safety. No output schema exists, but the result type is implicit.

  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 nip, bank_account, and date. The description does not add parameter-specific semantics beyond the schema, so baseline 3 applies.

  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?

  Description states 'Szybkie sprawdzenie TAK/NIE: czy KONKRETNY rachunek bankowy jest przypisany do KONKRETNEGO NIP-u', which clearly defines the check operation and distinguishes from sibling search_bank_account by explicitly positioning it as a confirmation check.

  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 'preferuj ten tool nad search_bank_account, jesli znasz OBA identyfikatory (NIP i numer konta) i chcesz tylko potwierdzenia' and mentions higher daily limit (5000 vs 100), giving clear context for selection.

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

• search_regonA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and idempotentHint, so the safety profile is known. The description adds behavioral context beyond annotations by mentioning the daily rate limit shared with the search method and enumerating possible errors (invalid_regon, invalid_date, not_found, rate_limit_daily, upstream_error). This enriches the agent's understanding of side effects and failure modes.

  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 two sentences long and efficiently structured: the first sentence states purpose and use case, the second adds rate limit and error information. No unnecessary words, and it is front-loaded with the essential purpose.

  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?

  For a simple search tool with two parameters, the description covers purpose, when to use, rate limit, and errors. It references search_nip for analogy, which implies similar output structure. The absence of an explicit return format is mitigated by the reference to the sibling tool and the simplicity of the operation.

  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?

  The schema description coverage is 100% for both parameters: 'regon' has a clear description with length constraints, and 'date' has a format and default value. The description reinforces the REGON length but does not add significant parameter semantics beyond the schema. Baseline 3 applies.

  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 it searches by REGON (9 or 14 digits) and distinguishes it from the sibling tool search_nip by specifying the search key difference. The verb 'wyszukiwanie' (searching) is explicit and the resource is named.

  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?

  It explicitly states when to use this tool: when you know the client's/contractor's REGON rather than NIP, which directly contrasts with search_nip. It also mentions the shared daily rate limit with the search method, providing a concrete usage constraint.

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

• search_nipA
  4.5/5.0
  Behavior5/5

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

  The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, but the description adds valuable behavioral context beyond those hints: it discloses the daily rate limit for the `search` method, lists specific error codes (invalid_nip, invalid_date, not_found, rate_limit_daily, upstream_error), and explicitly describes the return fields. This is a strong disclosure of operational behavior.

  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 a compact four-sentence paragraph, front-loaded with the primary purpose. It then efficiently covers return data, rate limits, and error codes without redundant explanations. Every sentence earns its place, and the structure is clean.

  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?

  There is no output schema, so the description correctly compensates by listing the returned fields (VAT status, name, REGON, KRS, address, registration/deregistration dates, bank accounts). It also addresses rate limits and possible errors. For a simple tool with two parameters, this is complete and actionable.

  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?

  The input schema already covers both parameters thoroughly: `nip` has format details (10 digits, optional hyphens) and `date` has format (YYYY-MM-DD) and default value (today). The description adds little parameter-specific meaning; it only reinforces that lookup is by NIP. With 100% schema coverage, the 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?

  The description uses a specific verb 'Sprawdza' and clearly identifies the resource: 'podmiot w Wykazie Podatnikow VAT (biala lista) po numerze NIP'. It distinguishes itself from sibling tools like search_regon and search_bank_account by specifying NIP as the lookup key and enumerating the returned data (VAT status, name, REGON, KRS, address, dates, bank accounts).

  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 clearly indicates when to use the tool: to verify a taxpayer in the VAT registry by NIP. It also provides practical usage context such as the daily limit (100/day per IP) and error codes. However, it does not explicitly mention alternative tools for REGON or bank account lookups, so it stops short of full when-not-to-use guidance.

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