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

Annotations already cover the read-only, non-destructive, closed-world profile, and the description adds substantial context on top: the payload is self-contained (partes, evidenceIds, checklist), results are ordered by nearest deadline and capped at 20, and the write step requires a connection-level minutas permission without which salvar_minuta does not appear. That permission-gating caveat is exactly the kind of behavior 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-loads the core purpose, filter, ordering and limit in the first sentence, with the workflow routing and permission caveat following. It is dense and the permission aside lands slightly out of sequence, but no sentence 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?

With no output schema, the description carries the return-shape burden and does so (complete package with partes, evidenceIds, checklist), while also covering the 20-item cap, the ordering rule, the permission prerequisite, and the next-tool chain. An agent has everything needed to call it and act on the result.

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?

Zero input parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description instead explains how the returned minutaProntaId feeds sibling tools, which is useful but concerns output rather than input semantics.

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 ("Lista") and a precisely bounded resource (pacotes de Minuta Pronta com status PRONTA_PARA_REDIGIR), plus ordering (prazo fatal mais próximo primeiro) and a cap (até 20). The status filter distinguishes it from the broader listar_minutas sibling without the agent needing to open either 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?

Gives an explicit trigger condition ("Use no início do prompt 'redigir minutas do dia'") and routes the agent onward by naming the exact downstream tools (dados_para_peca, ler_paginas, checar_peca, salvar_minuta) and the field to pass them (minutaProntaId). This is a full when-and-what-next instruction.

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