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

Beyond the annotations (readOnly=false, destructive=true, openWorld=true, idempotent=false), the description adds the two-phase confirmation contract, the fact that it acts under the connected Gover account's API permissions, the credential-handling prohibition, and the resultadoId hand-off for large payloads. It stops short of saying what the preparation returns or whether it creates pending server-side state, but the added operational context is substantial.

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 sentences with no padding; the phase constraint and the confirmation requirement come first and the secondary routing (resultadoId, payment data) comes last. Slightly list-like, but every sentence carries a distinct instruction.

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 high-complexity, deeply nested mutation-style tool with no output schema, the description covers the workflow, auth, and result handling well but leaves the parameter contract almost entirely unexplained. An agent can invoke it correctly at the process level but has no guidance on how to populate formData or the other identifiers.

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 0% across 8 top-level parameters with deep nesting, so the schema carries no field meaning. The description only says 'Os campos seguem o contrato da API' and that new payment data belongs in the Gover portal, which hints at the pagamento fields but explains no other parameter. With a very low coverage schema, the description needed to compensate and does not.

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 states a specific verb and resource ('Confirmar reserva e condicoes da solicitacao') and immediately clarifies the phase ('Prepara a acao, sem executa-la'), which resolves the tension between the tool name and its actual behavior. It also names the sibling that performs the execution (gover_confirmar_operacao), so an agent can separate the two phases. It loses a point only because the name 'confirmar_reserva' versus the 'preparar' behavior still requires the reader to reconcile two identities.

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 sequencing: display parameters to the user, and only after explicit confirmation call gover_confirmar_operacao; for long outputs call gover_ler_resultado with the returned resultadoId. It also states a hard exclusion ('Nunca informe credenciais ou identidade de autenticacao como argumentos') and a constraint on where new payment data may be entered. The alternative tool and the condition that selects it are named outright.

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