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

Adds meaningful behavior beyond the annotations: the tool does not execute, requires explicit user confirmation via a sibling, must not receive credentials, and escalates long output to gover_ler_resultado. It also constrains new payment data to the Gover portal. There is mild tension with destructiveHint=true for a tool described as non-executing, but the staged-write reading is defensible.

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?

The purpose is front-loaded and the sentences are short and directive, each carrying a distinct instruction (confirmation flow, credentials ban, pagination, payment data). Slightly list-like and repetitive around the API-contract point, but 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?

The workflow, confirmation, credential, and pagination aspects are covered, which is valuable for a prepare tool. However, for a tool whose sole argument is a complex nested form with no field documentation and no output schema, the definitions of what must be supplied are largely missing.

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% and the single 'form' parameter is a nested object of roughly eighteen undocumented fields (cnpj, unidadeTipo, tipoPagamentoId, etc.). The description only says 'Os campos seguem o contrato da API', which supplies no field-level meaning or required-field guidance, so it fails to compensate for the coverage gap.

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+resource ('Incluir unidade') and immediately clarifies it is a preparation step ('Prepara a acao, sem executa-la'), so the agent knows this stages rather than performs the creation. It separates itself from gover_alterar_unidade and gover_consultar_unidade by the 'include' action, though it never explicitly names those siblings.

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?

Clear workflow guidance: show parameters to the user, then call gover_confirmar_operacao only after explicit confirmation, and use gover_ler_resultado with the returned resultadoId for large results. It also states a usage constraint (never pass credentials as arguments). It does not, however, contrast itself against the sibling alterar/consultar unidade tools.

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