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

The description discloses behavior not present in the annotations: CPF/CNPJ are not public court search keys, the service maps CNPJ→razão social automatically, CPF requires the caller to provide nome_titular, and the operation is asynchronous returning { job_id }. These are substantive behavioral traits beyond readOnlyHint/idempotentHint/destructiveHint, and 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 carries critical information: what the tool does, the name-resolution caveat, the required nome_titular condition, the alternative tool, and the asynchronous polling flow. Key constraints are front-loaded and explicitly marked.

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 job-submission tool with no output schema, the description covers the core lifecycle: input, precondition, async response, and follow-up polling. It is slightly incomplete because the optional scoping parameters (platforms, tribunais, max_results) are not explained and the eventual result payload from processos_get_resultado is not previewed, but the most decision-relevant context is present.

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 has 0% property description coverage, so the description must compensate. It does explain the two least obvious parameters—documento as CPF/CNPJ and nome_titular as mandatory for CPF—but it leaves platforms, tribunais, and max_results semantically undiscussed beyond their names and enum/type. This is partial compensation, not full.

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 uses a specific verb and resource: 'DESCOBERTA por CPF ou CNPJ' and clearly explains the actual behavior—resolving the document to name(s) and searching by name. It also distinguishes itself from the sibling tool by stating the CPF-nome limitation and pointing to processos_buscar_por_nome as the alternative.

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 states exactly when to use this tool (when you have a CPF/CNPJ), what precondition applies (CPF requires nome_titular), and explicitly names the alternative for the case where the CPF holder's name is unknown: 'Sem o nome do titular do CPF, use processos_buscar_por_nome.' It also gives the follow-up action: poll with processos_get_resultado(job_id).

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