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

Annotations already declare destructive=true/idempotent=false, but the description adds real behavioral context beyond them: it is a prepare-only step, it uses only the connected account's permissions, it must not receive credentials, and payment data is handled elsewhere. The 'sem executa-la' wording sits in slight tension with destructiveHint=true, though this reflects the overall cancellation flow rather than a true contradiction.

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 the core purpose and the confirm-flow guidance, which is good. However, it runs several unrelated instructions together in one block and includes a payment-data note that is of dubious relevance to a cancellation tool, adding noise to an otherwise dense paragraph.

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 4-parameter, 0%-coverage tool with no output schema, the description covers the operational flow and result handling competently but leaves the parameter surface entirely unexplained. The usage workflow is complete; the field-level completeness is not.

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 coverage is 0% across 4 parameters (solicitacaoId, opcaoId, clienteId, justificativa), and the description does nothing to compensate—it only offers the boilerplate 'Os campos seguem o contrato da API'. No parameter's meaning, format, or the required/optional distinction is clarified, leaving the agent dependent on undocumented fields.

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 (cancelar solicitacao) and immediately clarifies the crucial nuance that it 'prepara a acao, sem executa-la', which distinguishes the two-phase prepare/confirm pattern from a direct cancellation. An agent can tell it apart from siblings like gover_aprovar_solicitacao or gover_confirmar_operacao.

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?

Explicit when-and-how guidance: show parameters to the user, then only after explicit confirmation call gover_confirmar_operacao, and for large results call gover_ler_resultado with the returned resultadoId. It names the alternative tools and the conditions that select them.

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