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

Annotations declare destructiveHint=true and openWorldHint=true, and the description adds substantial context beyond them: external government submission, certificate dependency, idempotency ('never submitted twice'), per-account live gating with test-environment fallback, and the returned registration number. An agent knows the blast radius, the auth prerequisites, and the sandbox behavior before calling.

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?

Four tight sentences: the action and return value come first, then prerequisites, then idempotency, then environment gating. No sentence repeats the schema or annotations, and nothing is padding.

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?

There is no output schema, but the description names the return value (número de registro). Prerequisites, idempotency, environment behavior, and the external-system nature are all covered, which is what an agent needs for a destructive, open-world submission tool.

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 67%: confirm and email are already documented in the schema, including the explicit-confirmation requirement, which the description merely reinforces. invoice_id is undocumented in the schema and the description only implies it must reference a finalized invoice, so it does not fully compensate for the gap.

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?

States a specific verb chain (sign with XAdES-EPES, submit) and the exact resource (FACe, the Spanish government invoicing gateway), plus the return value (número de registro). This clearly separates it from siblings like send_invoice, mark_invoice_sent, and get_face_status.

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?

Explicit preconditions are given: the invoice must be finalized, the customer must be flagged as public administration with three DIR3 codes, a digital certificate must be uploaded, and live submission must be enabled for the account (test environment otherwise). It does not name sibling alternatives such as get_face_status for status checks or send_invoice for non-B2G delivery, so the routing guidance is implicit rather than explicit.

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