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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds real operational context on top: it runs exclusively under the connected Gover account and its API permissions, accepts no credential arguments, and large payloads must be fetched via gover_ler_resultado. That is meaningful behavioral guidance beyond the annotation set, though it omits permission errors or result-size thresholds.

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?

Short, front-loaded, and each sentence carries a distinct rule (account scoping, read-only, no credentials, large results, payment data). The closing note about new payment data is tangential to a read tool but still a useful boundary.

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 7-parameter query tool with zero schema coverage and no output schema, the description addresses auth and result overflow but says nothing about what the cart contents look like or how the seven filters scope the result. An agent can call it, but cannot call it precisely.

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?

Seven filter parameters (termo, cidadeId, clientId, unidadeId, funcionarioId, tipoCentroDeCusto, finalidadeViagemId) have 0% schema description coverage, and the description compensates only with 'Os campos seguem o contrato da API' — it explains no parameter's meaning, format, or interaction. This leaves the caller guessing at the semantics of every input.

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+resource ('Consultar carrinho de compras do usuario') and clarifies the read-only nature ('Nao altera registros de negocio'), which separates it from mutating siblings like gover_remover_item_carrinho or gover_tarifar_carrinho. It does not, however, distinguish itself from other read siblings such as gover_consultar_solicitacao or gover_consultar_hospedagem explicitly.

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?

Provides one routing rule: for lengthy results use gover_ler_resultado with the returned resultadoId. It also implies the tool operates only on the connected Gover account. But it never states when to consult the cart versus browsing solicitation tools, nor any prerequisites or exclusions beyond credential handling.

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