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

Annotations already mark this as readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds value by noting that the query is against official public sources, has LGPD implications, and is hosted on the platform with no credentials, pay-per-query credit system. It clarifies the agent's responsibility regarding data privacy (controller = client, legitimate purpose). This gives behavioral context beyond annotations, helping the agent understand implications of the query.

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 solid paragraph that's efficiently written, covering the essential points: what it does, where data comes from, operational details (paid per query, no credentials), and legal note (LGPD). Though a bit long, it's well-structured and each sentence adds value. Could be broken into a few sentences but flows coherently without being overly verbose.

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 provides adequate context about the query source and legality, but several important details are missing: no explanation of what is done with the queried data (e.g., how results are returned), no mention of required input formats for parameters, and no specifics on which fields are mandatory beyond 'modelo' and 'email_envio'. For a tool with 14 parameters and no additional schema documentation, the description does not fully compensate for the lack of parameter details or 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 schema has 14 parameters with 0% description coverage. The description does not explain any parameters beyond mentioning 'modelo' and 'email_envio' implicitly. It doesn't clarify what 'modelo' (model/format) means in this context, nor the expected format for fields like 'birthdate' or 'naturalidade_uf'. Given the ambiguity, the description fails to compensate for the schema's lack of parameter 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 purpose is clearly described as consulting the registration of a certificate request at TJSP. It includes the scope (Brazilian official sources, same as available to citizens) and its directness to the correct source. While the exact operation is somewhat embedded in the tool name, the description provides valuable context that the data is from official Brazilian sources and not confidential, which helps disambiguate it from other possible operations like creating or canceling a certificate request.

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 explains this is for use with official Brazilian sources, but doesn't explicitly compare with alternatives. However, the statement about being for legitimate purposes (LGPD) and the no-credential, pay-per-query model gives context on when it's appropriate to use. Without listing alternative tools, it provides clarity that this handles public, non-confidential, official data queries, which implicitly guides usage.

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