Emitir en producción

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

The description adds significant behavioral context beyond the annotations: irreversibility ('No se puede deshacer'), the only remedy (credit note), the requirement of express approval, and the human confirmation gate. This is exactly the kind of safety-critical behavior an agent needs to know and is consistent with destructiveHint=true.

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 core action and irreversibility, then states the critical preconditions. Every sentence adds essential information; the parenthetical list of confirmation channels is slightly expansive but still useful for an agent deciding whether confirmation has occurred.

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 destructive, high-stakes tool with no output schema, the description covers purpose, environment, irreversibility, preconditions, and parameter matching. It does not describe the success/error response or post-emission workflow, but those are secondary to the safety-critical guidance it provides.

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 by explaining that numero, receptor, and total must exactly match the values returned by preparar_emision, and that mismatches prevent emission. It does not define borrador_id explicitly, but the draft context and tool name make it inferable. This is strong compensation for a fully undocumented 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 uses a specific verb ('EMITE') with a concrete resource ('COMPROBANTE FISCAL REAL') and environment ('ARCA producción'), clearly distinguishing this from preparation, validation, and confirmation tools. It is immediately obvious that this tool performs the real, irreversible emission.

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?

The description gives explicit when-to-use conditions: only after express user approval of this exact draft, with exact values from preparar_emision, and only after a human confirmation. It also states clear exclusions: if values do not match or confirmation is absent, no emission occurs. This fully routes the agent away from misuse.

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