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

Annotations already declare the tool as read-only (readOnlyHint=true) and non-destructive (destructiveHint=false), so the description doesn't need to repeat these. It adds the specific scope (SP state) and query method (by name), which is useful context beyond the annotations. However, it does not disclose potential side effects like rate limits or authentication requirements, though these are not critical for a simple certificate query. The description is consistent with the 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 extremely concise—a single sentence that immediately states the tool's purpose and scope. It avoids unnecessary verbiage and is easy to scan, which is ideal for an agent parsing tool definitions. No redundancy with the tool name or annotations.

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 is clear but somewhat incomplete for a tool that requires three mandatory fields. It doesn't specify the return format (e.g., PDF, text) or any additional requirements like age verification or data privacy considerations. However, the tool is conceptually simple (a lookup), and the lack of an output schema or nested objects reduces the need for extensive explanation. The missing clarity on required parameters and potential use cases makes it only moderately complete.

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 three required parameters (nome, genero, birthdate) with zero descriptions, and the tool description only mentions 'by name' ('por nome'), partially covering the 'nome' parameter. It fails to explain the need for 'genero' and 'birthdate', which are likely necessary for disambiguating individuals in criminal records. With schema coverage at 0%, the description carries the burden of explaining parameters, and it inadequately compensates, leaving agents uncertain about the purpose of these fields.

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 function: obtaining a criminal background certificate for the state of SP, with a focus on name-based queries. It specifies the resource (criminal records) and scope (SP state), which distinguishes it from sibling tools like 'consultas_sintegra_sp' or 'consultas_cnd_federal'. However, it doesn't explicitly differentiate from all siblings (e.g., other state-specific consultations), so it's clear but not fully distinguished.

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 that this tool is for querying criminal antecedents in São Paulo state, using the person's name. It gives a general sense of when to use it, but does not mention alternatives or when to avoid it. Sibling tools like 'consultas_antecedentes_federais' are not referenced, so an agent lacks explicit guidance on choosing between them. The context 'por nome' hints at the primary input, but there's no exclusion of other use cases.

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