send_einvoice

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description is not obligated to prove the tool is risky. It nevertheless adds information annotations cannot carry: the action is irreversible, correction requires a credit note, and dry_run exercises the full validation without side effects. It omits what validation output looks like or how rejections surface, keeping it below 5.

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 short sentences with zero padding, and the risk warning is front-loaded in capitals before the mechanics. The dry-run escape hatch comes last, in the natural reading order for a cautious caller.

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 an irreversible outbound integration with no output schema and no annotations describing return behavior, the description covers the danger but not the operational context: which document states are eligible for sending, what 'verifica' checks, and what the caller receives on rejection are all missing. Adequate, but not complete for a tool of this risk level.

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 only 33%, so the description needs to compensate. It does explain dry_run's semantics (full checks, no send), which the bare boolean default does not convey, and company_id is already documented in the schema. The required 'id' parameter – presumably the document to send – is never explained, so coverage remains partial.

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 compound verb and resource: 'Verifica l'XML e invia la fattura elettronica allo SdI'. An agent immediately knows this validates and transmits an e-invoice to the Italian exchange system. It does not explicitly distinguish itself from verify_einvoice or bulk_send_einvoice in the sibling list, so it stops short of a 5.

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 one concrete usage rule – dry_run=true runs all checks without sending – which usefully defines a safe preview path. However, it never states when to choose this over verify_einvoice (validation only), bulk_send_einvoice (batch), or email_document (delivery to recipient), leaving the agent to infer routing.

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