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

Annotations already indicate read-only and idempotent behavior; the description adds valuable context beyond those: no platform credentials are required, usage costs prepaid credits, the data is not confidential/secret, and LGPD compliance is explicitly put on the client side. This is useful behavioral/operational information that annotations do not capture.

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 short, front-loaded with the primary purpose, and each sentence adds relevant context such as cost, credential requirements, and LGPD implications. There is slight redundancy around "official sources" but the rest is efficient and useful.

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?

Despite good operational context, the description is incomplete for a handling agent: there is no output schema, no explanation of the returned CEAT certificate/content, and no guidance on how the three parameters relate or whether one is required. The tool has only a basic phrase, but for a realistic automated invocation, key invocation details are missing.

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 provides only names/types for cpf, cnpj, and nome, with 0% schema description coverage and no required properties. The description does not compensate: it never explains whether any identifier is required, whether CPF/CNPJ should be mutually exclusive, or what format/combination is valid. The property names provide some intrinsic meaning, but the tool cannot be reliably invoked based on current documentation.

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 names the exact action and resource: "Certidão Eletrônica de Ações Trabalhistas (CEAT), consulta em fonte oficial," making it clear that this tool queries the official TRT16 labor court certificate. It is immediately distinguishable from the sibling tools, which are platform operations like authenticate, connect, and marketplace.

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 clearly positions the tool for consulting official Brazilian public labor-labor data, notes that credentials are not needed, and states that prepaid credits are charged per query. It provides strong usage context, though it does not explicitly state exclusions or when NOT to use it, and there are no analogous court tools among siblings to compare alternatives with.

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