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

Despite annotations already flagging destructiveHint=true and idempotentHint=false, the description adds critical domain context: this is a legal act, the invoice cannot be recalled (only corrected via credit note), and it may be billed. It does not cover rate limits or error/response behavior, which keeps it just short of a 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?

Four short sentences, front-loaded with the WRITE marker and the legal warning. Every sentence earns its place: purpose, irreversibility, billing consequence, confirm semantics, and call-to-action.

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 two-parameter, high-stakes mutation tool with no output schema, the definition supplies everything an agent needs: what it does, what is destroyed, what the safe preview path is, and the required user-confirmation step. No material gap remains.

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 100%, so both parameters (uuid, confirm) are already fully documented, including the preview behavior of confirm=false. The description restates the confirm semantics rather than adding new meaning, so the baseline of 3 applies.

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 (transmit/send), the exact resource (draft invoice), and the destination system (Sistema di Interscambio). The 'WRITE:' prefix and the endpoint POST /invoices/draft/{uuid}/send make it immediately distinguishable from create_draft_invoice, get_draft_invoice, and delete_draft_invoice.

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?

Explicitly prescribes the workflow: show the draft to the user, get their explicit OK, then send with confirm: true. It also states what happens without confirm (preview-only return), so the agent knows the safe dry-run path and the irreversible path.

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