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

Goes well beyond the read-only annotations: totals span all pages and are not capped by the PDF's 500-row limit, ficha returns all entries plus a minimal client record, money is in BRL cents, and a paid marker merely sums value without proving receipt. It also discloses per-type permission requirements and the cursor continuation rule, which annotations cannot express.

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-loaded with purpose and filter mapping, and every sentence carries non-redundant information. It is dense to the point of being packed — semicolon chains like "iniciais para menores, vínculos paginados e link" take a second read — but nothing is filler.

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 9-parameter, 4-mode reporting tool with an output schema already defining returns, the description covers permissions, pagination, units, filter defaults, row caps and side-effect boundaries. An agent has everything needed to choose `tipo`, set filters and continue paging without trial and error.

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?

With 0% schema description coverage the description carries the burden and mostly delivers: it maps matéria/situação/responsável/cliente to processos, states that prazos defaults to pendentes (the `filtro` default), that mês/ano apply to vencimento in financeiro, that clienteId applies to ficha, and that cursor repeats the same filters. The one weak spot is that "responsável" is not explicitly tied to the `advogadoId` field name, leaving a small inference gap.

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 and resource ("Consulte dados estruturados para montar tabelas") and enumerates the four report shapes matching the `tipo` enum: processos, prazos, financeiro, ficha de cliente. It also implicitly separates itself from point-lookup siblings like consultar_financeiro, listar_prazos and buscar_clientes by framing itself as the aggregated, all-pages report source.

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?

Gives clear when-to-use (build report tables) and strong when-not exclusions ("Não gera arquivo, redige peça, altera registros ou envia a terceiros"), plus per-type prerequisites. It stops short of explicitly naming the sibling to use instead for a single process or a single client, so routing is inferable rather than stated.

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