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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint falseUTE. The description adds transparency about payment ('pague por consulta com crédito pré-pago'), data nature ('não é dado sigiloso'), and legal responsibility (LGPD). It also clarifies the source is official. This goes beyond the structured fields, though it doesn't detail response formats or potential errors.

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 a single sentence but concise, front-loading the purpose. It includes necessary context (payment, credentials, legal). It's not overly verbose, though the multiple clauses could be streamlined. Overall, it is efficient and to the point.

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?

The description covers purpose, payment, data source, and compliance. However, it does not explain expected output (e.g., the certificate format), which CPF/CNPJ to use, or any potential reasons for failure. For a simple query tool, this is acceptable but incomplete without an output schema.

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 lists two string parameters 'cpf' and 'cnpj' with no descriptions (0% schema coverage). The description does not mention these parameters or explain how they are used (e.g., one must be provided, or both are optional). Given the tool's purpose, parameters likely correspond to Brazilian tax IDs, but the description fails to clarify their semantics, leaving the agent without sufficient guidance.

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's purpose: 'Certidão Negativa de Débitos, consulta em fonte oficial' (Negative Debt Certificate, query in official source) from 'Prefeitura GO Goiânia' (Goiânia City Hall). This is a specific verb+resource (consult + certificate) and distinguishes it from generic siblings like authenticate or connect.

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 context: it is a paid consultation using prepaid credits, hosted by the platform, and accesses official Brazilian sources. It mentions 'sem credenciais da plataforma' (no platform credentials) and LGPD data control. However, it does not explicitly state when to prefer this tool over alternatives, though siblings are maintenance tools and not direct competitors.

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