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

Annotations already carry read-only, idempotent, and non-destructive hints, so the description focuses on genuinely useful behavioral detail: the `ausencia` block appears only on empty results, its possible reason codes, the mask tolerance for the process number, and the important caveat that `nao_publicado` does not mean the process does not exist. 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 core action and return shape are front-loaded, and every sentence contains substantive information. There is a slight redundancy between 'Só sem resultados inclui ausencia' and 'Com resultados, esse bloco não é retornado', but it is short and reinforces the contract rather than bloating it.

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?

Since there is no output schema, the description covers the top-level response fields, the no-result envelope, its reason codes, and the critical interpretation caveat. It leaves `total` and `count` semantics and the inner structure of `processos[]` somewhat unspecified, but 'metadados e movimentações por instância' provides enough working context for safe use.

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 prose must compensate. It explains that `numero_processo` accepts masked or unmasked formats, which is useful operational meaning. However, it does not elaborate on `tribunal` beyond the schema enum or describe the expected CNJ format, so the compensation is only partial.

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 ('Busca') and resource ('processo'), and pins down the exact lookup key: CNJ number plus court. It also names the return fields and states that the result includes movements per instance, which is enough to distinguish it from broader search or movement-only sibling tools without needing to mention them by name.

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?

Usage context is clear: call this when you already have the CNJ number and the tribunal, and you want the process plus its movements. The description also gives an explicit no-result procedural instruction: read the `ausencia` block before retrying in another tool. It does not explicitly name alternatives like datajud_search or datajud_movimentos, but the exact-match framing makes the intended use obvious.

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