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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral context: the CPF is only confirmed when corroborated across multiple companies, otherwise candidates are returned. It also warns about incomplete data due to LGPD and abstracts the source. This goes beyond annotations to clarify expected output and limitations.

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 moderately long but well-structured, starting with a clear layer designation and then explaining the process, usage, parameters, and caveats in a logical flow. Each sentence adds meaningful information, though it could be slightly more concise without losing key details.

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?

For a tool with no output schema, the description covers the return values (normalized profile or candidates), the confirmation logic, the follow-up option, and data caveats. It also addresses prerequisites (free text) and optional shortcuts (cnpj). Given the tool's complexity and missing schema, the description is sufficiently complete to guide an agent.

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%, so the description must explain all parameters. It does explain texto, cnpj, and seguir_dossie with purpose and usage. However, it entirely omits the 'nivel' parameter (basico/medio/avancado), leaving the agent without guidance on that important option. This is a significant gap for a tool with no schema descriptions.

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: identity discovery from free text, returning a normalized profile. It specifies the exact input (free text) and output (profile with name, CPF, companies, etc.), and distinguishes itself from the sibling tool capivara_dossie by explicitly stating when to use it (before capivara_dossie when CPF is unknown).

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?

Provides explicit usage guidance: use before capivara_dossie when CPF is unknown, provide texto with as much detail as possible, optional cnpj as a shortcut, and set seguir_dossie to true for a follow-up. This gives clear when-to-use and how-to-use instructions, and differentiates from the sibling.

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