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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that credentials are not needed and payment is required per query, which is useful. However, it does not disclose other behaviors like response time, potential failure modes, or rate limits, and it repeats the fact that data is not confidential, which is partially implied by openWorldHint=false? Actually, openWorldHint=false means the world is closed, but the description says the info is not confidential, which might be a slight contradiction? No, it's not a contradiction, but the description adds legal context about LGPD, which is extra. Overall, it adds minimal behavioral context beyond 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 three sentences, reasonably concise. However, the third sentence about the client being the data controller and LGPD responsibility is important but could be seen as verbose. The structure is adequate but not optimally front-loaded; the core purpose is in the first sentence. It earns its place but could be trimmed.

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?

Given the tool's moderate complexity (3 optional parameters, no output schema), the description covers the operational context (payment, credentials, data source) but misses parameter semantics and return details. Since no output schema exists, the description should explain what the query returns, but it does not. This is a significant gap for completeness.

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 coverage is 0%, meaning the description provides no parameter documentation. The parameters (cpf, cnpj, nome) are listed without any explanation of formats, constraints, or relationships (e.g., whether at least one is required, if they are mutually exclusive, or if combination is allowed). The description gives no guidance on how to fill them. With zero coverage, the description fails to compensate.

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 clearly states the tool queries the official CEAT labor lawsuit certificate from TRT15. It specifies the resource (Certidão Eletrônica de Ações Trabalhistas) and the action (consulta). However, it lacks explicit differentiation from possible sibling tools that might query other tribunals or similar certificates, though the tribunal name is in the tool 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?

The description provides clear context: it is a paid query with prepaid credits, hosted by the platform, and requires no platform credentials. It implies usage when needing official Brazilian labor court certificate data. However, it does not explicitly state when not to use it or mention alternative tools, but the sibling set is unrelated, so differentiation is less critical.

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