Server Quality Checklist

Tool Scores

• vera_sanctionsB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description discloses return values (risk_score, audit hash) and cost ($0.05 USDC via x402). However, it does not mention side effects, permissions, or operational details like rate limits or response format.

  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 extremely concise, conveying purpose, coverage, output, and cost in a single sentence. No unnecessary words.

  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?

  Given 3 parameters, no output schema, and no annotations, the description provides high-level purpose and output but lacks parameter descriptions and usage context. It is minimally complete for a simple tool.

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

  Parameters1/5

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

  Schema coverage is 0% and the description does not explain the three parameters (name, type, country). The description only mentions 'Sanctions screening' without linking to parameters, leaving agents to infer meaning.

  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 sanctions screening against specific lists (OFAC SDN, SARLAFT CO, etc.) and specifies the output (risk_score and audit hash). It distinguishes from siblings (vera_context, vera_entity, vera_rates) which cover different areas.

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

  Usage Guidelines2/5

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

  The description implies usage for sanctions screening but does not explicitly state when to use it versus alternatives, nor provide when-not-to-use guidance. No mention of prerequisites or exclusions.

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

• vera_ratesB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description adds limited behavioral context: a 5-minute cache and a cost of $0.02 USDC via x402. However, it does not disclose whether the operation is read-only, idempotent, or requires authentication.

  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-loads purpose, lists outputs, then adds caching/pricing. Every sentence adds unique value.

  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?

  Given no output schema and 0% parameter documentation, the description lacks details on return format, error handling, and the 'signals' parameter. It covers the core purpose but leaves gaps 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.

  Parameters2/5

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

  Schema coverage is 0%, so the description must compensate. It explains the 'country' parameter via its enum values, but the 'signals' parameter is completely ignored – no hint what values or purpose it serves.

  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 returns real-time central bank rates for specific LATAM countries and lists the exact rate names (TRM, DTF, IBR, TIIE, Selic, UF). It distinguishes itself from sibling tools like 'vera_context' or 'vera_entity' by focusing solely on rate retrieval.

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

  Usage Guidelines2/5

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

  No explicit guidance on when to use this tool versus alternatives. The description implies usage for LATAM country rates but does not explain when not to use it or mention sibling tools for context or sanctions.

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

• vera_entityA
  3.5/5.0
  Behavior3/5

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

  Without annotations, the description carries the transparency burden. It discloses the cost ($0.03 USDC via x402) and returns (NIT/CNPJ, status, etc.), but lacks details on idempotency, rate limits, or side effects. The behavioral info is partial but non-trivial.

  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 convey purpose, registries, outputs, and cost without extraneous words. The structure is front-loaded and efficient.

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

  Completeness2/5

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

  The description omits the additional countries (CL, PE) present in the input schema, creating inconsistency. It also does not explain how to use the optional 'name' parameter or the full set of registries. For a tool with no output schema, this leaves gaps.

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

  Parameters2/5

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

  Schema coverage is 0%, so description must explain parameters. It implies 'identifier' maps to NIT/CNPJ and 'country' determines the registry, but does not explain the 'name' parameter. The description adds some semantics but is incomplete for the optional name field.

  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 specifies the tool's purpose: 'Company enrichment from LATAM public registries' and lists specific registries (RUES CO, CNPJ BR, RFC MX) and return fields (NIT/CNPJ, status, representative, industry). It distinguishes itself from siblings (vera_context, vera_rates, vera_sanctions) by focusing on entity enrichment.

  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 usage for company enrichment but does not explicitly state when to use versus alternatives or provide exclusion criteria. The mention of LATAM registries gives context, but no guidance on prerequisites or conditional use.

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

• vera_contextA
  3.6/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the full burden. It discloses the cost ($0.10) and output types, but lacks details on authentication, rate limits, latency, or potential errors. The transparency is adequate but not comprehensive.

  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 single, concise sentence with structured output hints (arrow notation). Every word adds value, with no redundancy or extraneous information.

  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?

  The description lists expected outputs and cost, which is helpful for a simple tool with no output schema. However, it fails to explain the optional query parameter or any edge cases/limitations (e.g., restricted to LATAM). The completeness is adequate but has notable gaps.

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

  Parameters2/5

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

  The schema has 3 parameters with 0% coverage. The description explains sector and country but omits the optional 'query' parameter entirely. This leaves ambiguity for the agent on how to use query, reducing parameter semantics.

  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 provides AI-powered LATAM market context for a given sector and country, listing specific outputs (market_size, key_players, regulations, growth signals). This distinguishes it from siblings (e.g., vera_entity, vera_rates, vera_sanctions) which serve different purposes.

  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 market research inquiries but does not explicitly state when to use this tool versus alternatives. Sibling names provide context clues, but no direct guidance on exclusions or when not to use is given.

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