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

With no annotations, the description carries the full burden. It usefully discloses the e-mail side effect (send=true triggers a message to a person) and that item_ids reuses existing items from a diligence, but it says nothing about permissions, what object is created and returned, or what happens on duplicate/invalid cnpj.

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?

Five short clauses with the purpose front-loaded and no filler; each sentence carries branching logic. The telegraphic style ('certidoes e documents como em create_diligence') is dense but borders on under-specification rather than verbosity.

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 an 8-parameter mutation tool with zero annotations and no output schema, the description covers the main decision tree but omits return behavior, failure modes, and the meaning of two parameters. Adequate to attempt a call, not complete enough to call confidently.

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 coverage is only 13% (only 'to' documented), so the description must compensate: it explains the shape of 'to', the diligence_id/item_ids relationship, and the cnpj standalone mode. However it defers certidoes/documents to 'as in create_diligence' rather than defining them, and leaves message and name completely unexplained.

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 opening verb+resource ('Faz um pedido de documentos') is specific, and the description immediately branches into the two request modes (to="robot" for agency certificates vs. to={name,email} for a person via link). It also references create_diligence for the certificate/document vocabulary, which helps an agent separate it from list_requests and create_diligence, though it never explicitly states what those siblings do differently.

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?

It gives concrete selection conditions: use "robot" to request certificates from agencies, use {name,email} to request from a person, and only set send=true for e-mail if the user explicitly asked. It also distinguishes the in-diligence path (diligence_id, item_ids) from the standalone path (cnpj). No exclusions against sibling tools like request_documents are stated.

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