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

The annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds minimal behavioral context beyond that, such as the scope of data (societary links). However, it doesn't disclose details like whether results are limited to direct links or include indirect relationships, schema coverage is absent, and no output schema exists. It doesn't contradict the annotations; it just doesn't add much depth.

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

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

The description is extremely concise: a single sentence that states the purpose. No fluff or redundancy. However, it likely sacrifices necessary detail for brevity, so it's not a 5. It's appropriately structured with the key concept front-loaded.

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

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

Given the tool has 3 parameters, no output schema, low schema coverage, and minimal annotations, the description should provide more context. It only states the general purpose, omitting details on parameter usage, outbound data structure, or limitations. Compared to the calibration examples, it's similar to 'update_drive' which scored 2 on completeness because it didn't explain behavior or output for a mutation tool. Here, the tool is a read operation, but still lacks parameter and output context, and the description adds little beyond the name and title.

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

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

The input schema has three parameters (CPF, CNPJ, completo) with zero description coverage. The tool description does not explain what these parameters mean or how they interrelate (e.g., whether CPF and CNPJ are mutually exclusive, what 'completo' implies). The description only mentions 'person or company', hinting that CPF relates to a person and CNPJ to a company, but it's not explicit. Since schema coverage is 0%, the description should compensate but doesn't effectively, leaving the agent guessing on parameter usage.

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

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

The description 'Vínculos/relacionamentos societários de uma pessoa ou empresa' clearly states the tool's purpose: it retrieves corporate links/relationships for a person or company. While it names the exact resource (societários links), it doesn't explicitly distinguish it from sibling tools like investigacao_participacoes, which might have overlapping scope, hence a 4 instead of 5.

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

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

The description implies usage by indicating the type of subject (person or company), but it does not provide explicit guidance on when to use this tool versus alternatives like investigacao_participacoes or investigacao_beneficiario_final. It lacks any 'use this instead of X' or conditional context.

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