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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds high-value behavior beyond those annotations: the upstream returns ALL commissions' agendas and filtering is local, large windows can trigger payload errors, intervals across years are split internally, and the exact response envelope is stated. There is no contradiction with the 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?

The description is dense but every sentence earns its place: core purpose, a critical upstream limitation with a workaround, response shape, and cross-references to related tools. The most actionable information is front-loaded, and the paragraph structure makes the warning visible before the user commits to a broad query.

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 read-only listing tool with an output schema and read-only annotations, this description is complete. It covers input defaults, date format, the error-prone condition, output structure, and the surrounding tool workflow. An agent has everything needed to invoke it correctly and to route follow-up calls to senado_reuniao_comissao.

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?

The schema only documents names, types, and the YYYYMMDD format, while the description adds real semantics: both date params are optional together and default to the last 14 days, the sigla filter is applied locally rather than upstream, and the recommended window size for dataInicio/dataFim is explicitly provided. This goes well beyond the baseline for a 100% schema-covered parameter set.

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 opens with a specific verb and resource: 'Lista reuniões de uma comissão (pela sigla)' in a date interval. It clearly differentiates itself from senado_reuniao_comissao by stating that the latter is for 'detalhes da pauta', and from senado_listar_comissoes by prescribing it for discovering the sigla. No ambiguity remains about what this tool does.

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 explicit operational guidance: default behavior without dates ('sem datas, usa os últimos 14 dias'), a strong recommendation to keep windows up to 2 weeks, and how to handle larger periods by splitting into successive calls. It also names the exact sibling tools to use before and after this one, making the call workflow explicit.

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