Server Quality Checklist

Tool Scores

• fr_compliance_checkA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the burden. It names data sources (SIRENE, VIES, BODACC) and outputs, but does not disclose behavioral traits such as external API calls, rate limits, permissions, or potential side effects. It is read-only in nature but this is not confirmed.

  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?

  A single sentence that covers the main functionality and outputs. It is front-loaded with the main purpose. Slightly more structure (e.g., bullet points) could improve readability but it is concise and effective.

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

  Completeness3/5

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

  No output schema exists, so the description must explain return value. It mentions risk signals, a score (0-100), and level (faible/moyen/eleve), which is adequate. However, it does not specify the format or structure of the risk signals, leaving some ambiguity for an agent.

  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%, with both parameters having descriptions. The tool description adds context that the SIREN can be 9 or 14 digits and explains the response_format options, reinforcing but not significantly extending 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 performs a comprehensive KYC check from a SIREN, listing specific checks (administrative status, VIES validation, BODACC procedures, seniority) and outputs risk signals, score, and level. It is distinct from sibling tools which focus on individual components.

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

  Usage Guidelines3/5

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

  The description implies use for KYC compliance but does not explicitly differentiate from siblings like fr_vat_compute or fr_bodacc_search. No guidance on when to use this combined tool vs. individual tools.

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

• fr_bodacc_searchA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It mentions the data source (DILA open data) and the types of announcements, but lacks details on rate limits, pagination, error handling, or output structure beyond format options.

  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: the first lists functionality, the second provides a practical use case. No wasted words, front-loaded with key 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 complexity (6 parameters, no output schema), the description covers the essential behaviors. It mentions return formats (markdown/json) and filter families. Could be more explicit about output fields, but adequate.

  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% with descriptions for all 6 parameters. The description adds value by explaining priority ('prioritaire sur query' for siren) and specifying that 'procol' targets collective procedures, going beyond 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 BODACC legal announcements by SIREN or denomination, listing specific types of announcements (creations, modifications, etc.). This distinguishes it from sibling tools like VAT and compliance checks.

  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 clear use case: 'Utile pour detecter une defaillance avant de contracter' (useful to detect a failure before contracting). While it doesn't specify when not to use or alternatives, the context is sufficient given sibling tools are unrelated.

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

• eu_vat_validateA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses real-time validation, return of company name and address if published, and coverage. It does not mention rate limits, authentication, or side effects, but the core behavior is transparent enough.

  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, front-loaded with action verb 'Verifie'. No redundant words; 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?

  Given the tool's simplicity (2 parameters, no output schema), the description sufficiently covers purpose, data source, coverage, and output format. No gaps.

  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 tool description adds no extra meaning beyond the schema, thus meets the baseline expectation.

  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 validates a VAT number in real-time via the VIES service, returning company name and address. It specifies coverage of 27 EU states plus Northern Ireland, distinguishing it from siblings like fr_vat_compute which likely computes French VAT.

  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 indicates when to use (to validate an EU VAT number) and implies it is for real-time verification. However, it does not explicitly state when not to use or mention alternatives, though the sibling tools provide context.

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

• fr_vat_computeA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It effectively discloses that the computation is local and instantaneous with no network dependency. However, it does not mention error handling or validation behavior for invalid inputs.

  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: two sentences that cover the core functionality and usage context. No redundant 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?

  The description is adequate for a simple computation tool. It covers purpose, usage, and behavioral traits. It could benefit from mentioning error handling or the expected return value, but overall it provides sufficient context given the lack of output schema.

  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%, so baseline is 3. The description does not add additional meaning beyond what the schema already provides for the two parameters (siren and response_format). The schema already includes descriptions and defaults.

  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 computes the French intra-community VAT number from a SIREN/SIRET, validating the Luhn key. It specifies the output format (FR + 2-digit key + SIREN) and distinguishes from sibling tool eu_vat_validate by stating it should be used before when only the SIREN is known.

  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?

  The description explicitly says when to use: before eu_vat_validate when only the SIREN is known. It also notes it's a local instant computation with no network call, providing clear context for tool selection.

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