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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is given. The description goes beyond them with genuinely useful behavior: authorization is bound to the connected account and its API permissions, credentials must never be passed as arguments, oversized results must be fetched via gover_ler_resultado with a resultadoId, and new payment data may only be entered in the Gover portal. Only the return/pagination shape of this call itself is left unexplained.

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?

Each sentence is short and carries a distinct constraint, and the critical guidance (auth model, follow-up tool) is front-loaded. There is mild redundancy ('Nao altera registros de negocio' merely echoes the annotations) and a filler line about the API contract, but overall it is efficient.

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 nine-parameter search tool with no output schema and no enum guidance, the description covers authorization, follow-up reading and a payment-data restriction but says nothing about how to build a query from the nine filters. An agent can call it safely but cannot scope it meaningfully.

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?

Nine parameters with 0% schema description coverage, and the description dismisses them entirely with 'Os campos seguem o contrato da API'. None of termo, cidadeId, clientId, filialId, clienteId, unidadeId, funcionarioId, tipoCentroDeCusto or finalidadeViagemId is explained, so the description fails to compensate for the complete absence of schema documentation.

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 opening sentence restates the title almost word-for-word ('Pesquisar unidades para a viagem'), adding only the scope 'para a viagem'. It does name a verb (pesquisar) and resource (unidades), but it never distinguishes itself from the extremely close sibling gover_pesquisar_unidades, which an agent would have no way to choose between. Minimum-viable identification, not a differentiating one.

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 conveys useful operating context: the search runs under the connected Gover account, and large result sets must be followed up with gover_ler_resultado using the returned resultadoId. However, there is no statement of when to use this tool versus gover_pesquisar_unidades or gover_consultar_unidade, leaving the main selection decision to inference.

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