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

Adds substantial context beyond the annotations: warns that re-creating may discard in-progress quotation products (explaining the destructive/non-idempotent behavior), states it uses exclusively the connected Gover account and its API permissions, and forbids passing credentials as arguments. These are real behavioral constraints the annotations alone do not convey.

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-loads the core intent ('Criar solicitacao') and each following sentence carries a distinct instruction (destructive retry, alternatives, auth, confirmation flow, result retrieval). Dense but not padded for a complex multi-step tool.

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?

Given a 9-param tool with nested objects, no output schema, and a two-step confirmation workflow, the description covers the operational flow, auth, alternatives, and how to retrieve large results via gover_ler_resultado. The main gap is per-parameter semantics, which it defers to the API contract.

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 only 11% and there are 9 params with deep nested objects, so the description carries a heavy burden. It does add meaning for planejamentoId (what fields are inherited from the planning and which complementary fields the form then accepts) and payment-data handling, but it otherwise punts with 'Os campos seguem o contrato da API', leaving most parameters undocumented.

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 ('Criar solicitacao') and clarifies the crucial nuance that it prepares the action rather than executing it. It distinguishes from siblings by pointing to gover_planejar_cotacao and casting creation as a prerequisite for gover_cotar_voos, though it does not explicitly distinguish itself from gover_iniciar_solicitacao.

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/when-not/alternative guidance: 'Nao use criacao para corrigir uma solicitacao existente', 'Prefira gover_planejar_cotacao e informe planejamentoId', and the confirmation routing via gover_confirmar_operacao after explicit user confirmation. Nothing is left to inference.

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