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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely useful context: it runs exclusively under the connected Gover account and its API permissions, credentials must never be passed as arguments, and large result sets require a follow-up call to gover_ler_resultado. It does not describe rate limits or the shape of the result handle beyond the id.

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?

It is short, front-loaded with the purpose, and each sentence carries a distinct point (auth scope, no business mutation, credential handling, result handoff, portal-only payment data). Some security boilerplate is arguably redundant with the annotations, but nothing is bloated.

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 tool with a very rich nested input schema, no output schema, and zero parameter documentation, the description is far too thin: it never explains formData structure, required identifiers, or the enum semantics. The one concrete behavior it does document (resultadoId handoff) helps, but the whole parameter surface remains unexplained.

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 plus a deeply nested formData object (dozens of fields, including a tipo enum with 100+ opaque numeric values). The description adds nothing except 'os campos seguem o contrato da API', which does not compensate for the coverage gap. This is a clear case where the statement must do more 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 largely restates the title ('Obter opcoes para pesquisa de voos') and gives only a vague sense of the action. It never distinguishes itself from the many overlapping siblings such as gover_buscar_voos, gover_cotar_voos, gover_consultar_resultados_voos or gover_validar_pesquisa_aerea. The only extra signal is the mention of a resultadoId, hinting this initiates a search that may return a handle.

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 partial routing: for extensive results the agent is told to use gover_ler_resultado with the returned resultadoId, and it warns that new payment data must be entered in the Gover portal. However it never says when to call this instead of buscar_voos/cotar_voos, nor any prerequisites for starting an air search.

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