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

Adds real context beyond the annotations: it discloses the external dependency on Receita (reinforcing openWorldHint), the idempotent-collapse behavior with the ja_existia flag, and the chaining contract (retorna tipo + id para emitir_nota). It does not mention auth/permission requirements, which would be the remaining gap for a create operation.

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?

Three tight sentences, zero filler, and the primary branching rule plus the return contract are front-loaded. Every clause carries information an agent needs.

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?

With no output schema, the description compensates by naming the returned fields (ja_existia, tipo, id) and their downstream use. Combined with the CNPJ/CPF branching and idempotency note, there is nothing essential left for an agent to guess.

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 100% and both parameters already carry descriptions covering the CNPJ/CPF and punctuation tolerance, so the description largely restates the schema (nome obrigatório para CPF). No added syntax, format, or validation detail beyond what the schema states — baseline 3 applies.

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?

Specific verb + resource ("Cadastra um cliente") with the two supported identity paths spelled out (CNPJ auto-filled from Receita, CPF requires full name). An agent can distinguish this from listar_tomadores or consultar_cnpj by the act of creation, though no sibling is named explicitly.

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?

States the selection rule between the two modes (CNPJ → only documento needed, data sourced from Receita; CPF → must supply nome) and warns that an existing record is returned rather than duplicated. Lacks an explicit "check with consultar_cnpj/validar_cnpj first" exclusion, so it stops just short of full when/when-not coverage.

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