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

Annotations already declare destructive=true, openWorld=true and non-idempotent, so the safety profile is covered. The description adds genuinely non-obvious behavior: the tool prepares but does not execute, it requires downstream explicit confirmation, it ignores credentials, and its fields must conform to the API contract. It stops short of describing side effects of the eventual change or permission failures.

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 action and the prepare-vs-execute model, and most sentences carry distinct operational value (confirmation loop, credential prohibition, resultadoId routing). The trailing note about payment data in the Gover portal is tangential 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 complex, destructive mutation with no output schema and a nested, fully undocumented payload, the workflow and safety guidance are solid, but nothing explains what the nested fields mean or which are required for an alteration. An agent would have to guess at the payload shape.

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 deeply nested object with roughly fifteen candidate fields (centroDeCustoId, acao, gestores, etc.), none of which are documented. The description only says fields 'follow the API contract', which adds no meaning an agent can act on, so the nested structure is essentially opaque.

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 ('Alterar centro de custo') and immediately qualifies it as the preparation half of a two-phase mutation, explicitly naming gover_confirmar_operacao as the execution step. This distinguishes it cleanly from the confirm sibling and from the read sibling gover_consultar_centro_custo.

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?

Gives the full operating procedure: show parameters to the user, obtain explicit confirmation, then call gover_confirmar_operacao; and route to gover_ler_resultado with the returned resultadoId when output is large. It also states two exclusions – never pass credentials as arguments, and fill new payment data only in the Gover portal.

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