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

Annotations already mark it as read-only, non-destructive, and idempotent. The description adds valuable behavioral details: it does not require platform credentials, it is a paid consult (prepaid credit), and the data is not confidential. It also clarifies data controller responsibilities (LGPD). This goes beyond the annotations and helps the agent understand implications like cost and data handling.

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 paragraph, relatively short, and front-loaded with the tool's purpose. It includes essential metadata (official source, no credentials, payment model, LGPD responsibility) without excessive fluff. However, it could benefit from a bulleted structure for readability, though it is still concise.

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 that there are 8 parameters and no output schema, the description leaves much to be inferred. It explains the nature of the query (official, safe, paid) but does not explain what inputs are needed or what to expect in return. Since the tool has many parameters ordered without explanation, the description is insufficient for a complete understanding. A score of 3 reflects that it covers the 'what' and 'why' but not the 'how'.

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%—the description explains none of the 8 parameters. It does not mention what 'chave_infracao', 'placa', 'obter_desconto', 'login_cpf', 'login_senha', 'pkcs12_cert', 'pkcs12_pass', or 'cnpj' mean. Given the tool has multiple parameters, the description should have at least explained the key ones. This is a critical gap, as the user cannot understand which parameters are required for what purpose.

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 Brazilian traffic fine billets (Boleto da Infração) from the official SENATRAN source. The verb 'consultar' (query) and resource 'Boleto da Infração' are specificтно named. It is easily distinguished from the generic sibling tools (authenticate, connect, etc.).

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 indirect usage context—official source, no platform credentials needed, pay-per-query, and LGPD compliance—but does not explicitly state when to use this tool over alternatives or exclude cases (e.g., if the fine is already paid). No comparison to other tools is provided, so it only implicitly indicates its purpose.

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