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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses pricing, response time, response format (summary + .md file), token size limitations, the fact that data may be incomplete/outdated, and LGPD compliance. It clearly states the extra cost and authorization requirement for SCR, providing full transparency about how the tool behaves.

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 quite long but well-organized: first the purpose, then details for PF/PJ, then pricing/levels, timing, SCR requirements, response format, and legal caveats. Every sentence adds essential information, though a bit dense. It is front-loaded with the core purpose and ends with necessary caveats.

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?

For a tool with 6 parameters and no output schema, the description covers all necessary operational aspects: input selection, level choices, costs, time expectations, response structure (with reference to arquivo_ler), authorization handling, and data reliability caveats. It leaves no obvious gaps for an agent to successfully invoke and interpret the tool.

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 schema provides only parameter names and types, with no descriptions (coverage 0%). The description compensates fully: it explains that cpf_or_cnpj selects person/company, that nivel determines price and scope, that formato=resumo is default (summary + .md) while completo is for programmatic use, and that autorizacao_titular_scr gates restricted data. This is far beyond what the schema offers.

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 clearly states the tool's purpose: a 360º background check ('Raio-X cadastral') for either a person (by CPF) or company (by CNPJ), consolidating data into a report. It distinguishes itself from siblings like 'capivara_resolver' and 'capivara_registrar_consentimento' by being a comprehensive, multi-source dossier tool.

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?

It gives explicit usage instructions: provide either cpf or cnpj, choose a nivel (with pricing), and note that SCR data requires authorization and is charged extra. It advises informing users about long wait times for the 'avancado' level and mentions that 'formato=completo' is for programmatic use. It does not explicitly name alternative tools, but the context is sufficient.

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