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

Annotations already mark the tool as readOnly, idempotent, and non-destructive. The description goes well beyond annotations by explaining polling behavior, status transitions, degraded 'done' responses, the meaning of vinculacao_nome 'nao_confirmada', and the interpretation of tribunais_inacessiveis. This is rich behavioral context that an agent cannot infer from the schema or annotations alone.

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?

Though dense, every sentence carries operational value. It front-loads the core purpose, states the return structure, gives the polling loop, and then provides essential data-quality warnings. No filler is present, and the structure moves naturally from basic behavior to critical caveats.

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?

There is no output schema, so the description correctly explains the response fields, statuses, and item contents. It also covers the most important safety caveats around degraded results. The main gaps are the undocumented job_ids parameter and the lack of guidance for what to do on status 'error' instead of only 'done'.

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%, so the description must compensate for undocumented parameters, but it does not. It never explains job_id vs job_ids, whether job_ids is a batch alternative, how the required job_id is obtained, or how parameters affect polling. The generic phrase 'de um job de busca' is the only hint, which is insufficient for two parameters with zero schema 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 specific verb and resource: 'Polling de um job de busca' and explicitly ties the tool to processos_buscar_por_nome/documento. It clearly describes what the tool returns and distinguishes it from the search tools themselves, so an agent can understand its role without confusion.

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?

The description gives clear operational guidance: 'Continue chamando até done' and 'a busca é lenta', which tells the agent when and how often to call. It also warns about degraded 'done' results and when not to present data confidently. However, it does not explicitly state when not to use the tool or mention any alternative polling mechanism, though the source-tool reference makes the intended context clear.

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