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

With only openWorldHint annotation, the description carries the burden of explaining the tool's behavior. It discloses that the tool requires an already authorized NF-e and directs the user to provide the original key in NFReferencia, adding meaningful behavioral context beyond the annotation. It does not enumerate all technical side effects (e.g., SEFAZ submission), but the essential behavior is transparent.

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?

Two sentences with no fluff. The first states the core action, the second gives the use case and the key parameter. Information is front-loaded and every word earns its place.

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?

Given the tool has 16 parameters and a complex fiscal domain, the description is minimal. It omits guidance on TipoComplemento, ImpostoComplementar, and how to handle item-level complements. The output schema may cover return values, but an agent would struggle to know the full set of considerations for correct usage, so the description is merely adequate.

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 description explicitly instructs to pass the original invoice key in NFReferencia, adding meaningful value beyond the schema's vague 'Notas fiscal de Referência'. With schema coverage at 56%, highlighting this critical parameter helps agents avoid misusing the tool. However, it does not clarify the distinction between TipoComplemento values or the ImpostoComplementar structure, so it's not a 5.

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 emits a complementary NF-e referencing an already authorized NF-e, using the specific verb 'Emite' and the resource 'NF-e complementar'. It distinguishes itself from sibling tools like nfe_emitir through the qualifier 'complementar' and the explicit finalidade=2 context.

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 provides clear usage context: for complementing values, taxes, or items of an already authorized invoice. It does not explicitly name alternative tools (e.g., nfe_emitir for normal invoices), but the reference to a previously authorized NF-e and finalidade=2 gives an agent enough context to select this over a regular emission.

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