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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial unique behavior: data provenance (CVM open data, ODbL, daily file), no completeness/freshness guarantee, disclaimer that it is not legal or financial advice, explicit absence of PII, the interpretation of `registrada: false` with `fonte: ok`, the possibility of multiple registros with the non-cancelled one first, and download failures surfacing in `fontes`.

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?

Front-loaded with purpose, then the when-to-use block, then provenance and edge-case semantics — a logical ordering where each paragraph earns its place. Slightly long and the CNPJ format note duplicates the schema, but there is no filler.

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?

An output schema exists, so return values need not be enumerated, yet the description still supplies the interpretive keys an agent needs (registrada:false vs fonte:ok, multiple registros ordering, fontes on failure). For a mutation-free single-parameter lookup this is complete.

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?

Schema description coverage is 100%, so validation rules and accepted formats (14 digits, with or without punctuation, check digits validated) are already fully documented in the schema. The description's 'com ou sem máscara' simply restates that, adding no new parameter meaning — baseline 3 applies.

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?

States a specific verb and resource — 'Registro de companhia aberta na CVM por CNPJ' — and scopes it to the CNPJ lookup. An agent can distinguish this from cadastro_empresa, sancoes_empresa or contratos_publicos without opening any schema.

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?

An explicit 'Quando usar' block states the question this tool answers (whether the company is a registered open company, its status, category and auditor) and names the sibling to use instead for the full view: relatorio_completo. Both the trigger and the alternative are given, leaving nothing to inference.

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