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

The description adds rich behavioral detail (real fiscal document, confirmation warning, idempotency key, error handling), but it contradicts the annotations. It says the tool creates a real external fiscal document, while openWorldHint=false claims a closed world, and it presents external_id as an idempotency key while idempotentHint=false says the tool is not idempotent. This is a serious annotation inconsistency.

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 front-loaded with the action and a high-stakes warning, then uses a bullet list for key parameters and error guidance. Every sentence earns its place and the structure is easy to scan.

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 no output schema and a complex fiscal-emission operation, the description is complete enough: it states the return value (id and processing status), explains idempotency, covers the main failure mode, and provides the required payload shape. The only minor gap is the company parameter.

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?

With 0% schema description coverage, the description compensates substantially by documenting the required nfse JSON fields (cityServiceCode, description, servicesAmount, borrower) and explaining external_id as an idempotency key plus external_ids for bulk. It omits the company parameter, but overall adds significant meaning beyond the bare schema.

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 states a specific verb and resource ('Emite uma NFS-e'), clarifies it creates a real fiscal document, and distinguishes the tool from siblings such as cancelar, consultar, and listar. An agent can tell what this tool does without opening the schema.

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 clear operational guidance: confirm data before calling, reuse external_id to avoid duplication, and do not retry when the company is not enabled — instead check notafiscal_empresas. It lacks general when-to-use routing against other notafiscal siblings, but the error-path alternative is explicit.

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