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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is known. The description adds meaningful behavioral context beyond that: the hard constraint 'informe ao menos um critério', the default/max limit (100/500) with aviso when truncated, accepted date formats (YYYYMMDD or ISO), and the ordering/limit formula for recency queries. No contradiction with 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?

Although the description is long, every sentence earns its place: purpose, minimum criteria, recency recipe, return shape, sibling routing, limit behavior, and examples. The main verb and resource are front-loaded, and the structure flows from what the tool does to how to invoke it to what to expect.

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 11 parameters, an output schema, and annotations, this description is remarkably complete. It covers required criteria despite zero required params, explains ordering and limits, describes the return structure, disambiguates from senado_obter_materia, and gives both a keyword-style and an exact-lookup example. Nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds significant value: it maps natural-language request types to parameter combinations (palavraChave+ano+limite for recent matters; sigla+numero+ano for precise lookup), explains when to use ordenarPor/ordem with dataApresentacao, and provides two concrete JSON examples. This goes well beyond the schema field descriptions.

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 clear verb-resource pair, 'Busca matérias legislativas', and enumerates the filter dimensions (tipo, número, ano, palavras-chave, autor, período, situação). It also explicitly distinguishes itself from senado_obter_materia by saying the latter is only for detail/tramitação/textos, so an agent can tell them apart without opening the schema.

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 when-to-use patterns ('Para pedidos como matérias recentes sobre X, use...' with concrete parameter combinations) and an explicit when-not-to-use statement: 'não é necessário chamar detalhes para listar resultados' and 'Use codigo em senado_obter_materia apenas quando o usuário pedir detalhe/tramitação/textos'. This routes the agent to the correct sibling and prevents unnecessary follow-up calls.

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