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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds genuinely new context: it runs under the connected Gover account's API permissions, credentials must never be passed as arguments, extensive results continue via resultadoId, and payment data is only entered on the portal. The pagination-continuation behavior in particular is not derivable from annotations.

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?

Purpose is front-loaded and the resultadoId rule is useful, but several sentences are boilerplate that read as generic policy ('Nunca informe credenciais...', 'Dados de pagamento novos devem ser preenchidos somente no portal Gover') and contribute little to invoking an airport lookup correctly.

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 simple, read-only, single-parameter search with safety already covered by annotations, the description covers auth and result-continuation adequately and hints at the resultadoId return. But with no output schema and a completely undocumented parameter, an agent still lacks the input contract needed to call it confidently.

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% for the single required 'Texto' parameter. The only compensation is the generic 'Os campos seguem o contrato da API', which explains nothing about what Texto should contain, its length limit, or matching behavior (partial name vs code). This leaves the primary input 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?

The opening sentence 'Pesquisar aeroportos' is a verb+resource statement but is a literal restatement of the tool name/title, so it earns no differentiation. With ~90 sibling tools including gover_buscar_cidades_hotel and gover_buscar_bairros_hotel, nothing here tells the agent how this search differs from the other lookup tools.

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?

It gives one concrete routing rule -- for long results use gover_ler_resultado with the returned resultadoId -- which is real usage guidance. However it never says when to choose airport search over the sibling city/locale lookups, so most selection decisions are left to inference.

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