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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which the description aligns with via 'consulta' and adds no contradiction. The description enriches the picture by disclosing cost implications ('pague por consulta com crédito pré-pago'), hosting specifics ('Hospedado pela plataforma, sem credenciais da plataforma'), and legal/data-handling context ('O cliente é o controlador dos dados e responde pela finalidade legítima (LGPD)'), which are not available in structured form.

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 crams purpose, hosting, billing, data source claims, and legal responsibilities into four dense sentences, front-loading the core purpose in the first sentence. While every sentence adds some value, the structure is a run-on paragraph that mixes unrelated concerns (cost, LGPD, hosting) and could be better separated for consumption despite being information-rich.

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 with three params, no output schema, and no annotations on return values, the description compensates well by covering commercial, legal, and data-origin context. However, it omits any insight into the response structure, parameter usage, or error handling, leaving a noticeable gap in what a complete tool description should specify for an agent to invoke it fully.

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 input schema defines three string parameters (cpf, cnpj, nome) with 0% description coverage, and the description provides zero explanation for any of them. Since none of the parameters are required and the description doesn't clarify which identifier is needed or acceptable combinations, an agent cannot reliably determine required arguments, though the names are self-evident in the Brazilian context.

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 identifies the tool as a query for the 'Certidão Eletrônica de Ações Trabalhistas (CEAT)' from 'Tribunal TRT7', specifying a particular verb ('consulta') and resource. It specifies the tool is a read operation on an official Brazilian source, and the context properly differentiates it from the sibling tools like 'authenticate' and 'connect' by describing a specific domain query. The purpose is unmistakable even with the dense language.

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 implies usage context by emphasizing content is from 'fontes e órgãos oficiais brasileiros (a mesma disponível ao cidadão), não é dado sigiloso', indicating when this is appropriate for public-data queries and LGPD compliance. However, it lacks explicit with-exclusion statements, alternatives, and prerequisites, so an agent would not have clear guidance on when NOT to use this tool vs. alternatives.

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