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

The description goes far beyond the annotations by disclosing deterministic extraction ('NON sono inferiti da un LLM'), exact validation logic (MOD-97, ABI, P.IVA/CF checksums), live VIES behavior with honest degradation ('degradare ONESTAMENTE ad attenzione, mai a un falso ok'), and external I/O limits (one VIES query per call). It also adds cost and authentication context ('Gratis (€0), nessun login'). This is consistent with readOnlyHint since the external I/O is a read-only lookup.

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 long but dense and every clause earns its place: extraction, verification checks, verdict scale, multi-IBAN handling, VIES budget degradation, cost/auth, and the out-of-band caveat. The verb and scope are front-loaded, with the most important operational constraints following logically.

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 complex tool with no output schema, the description covers return content (parse + supplier_verification verdicts/red flags), failure modes (VIES unreachable, shared budget exhausted), the external I/O constraint, and the safety caveat about out-of-band verification. The input contract is already documented in the schema, so nothing essential is missing for correct invocation.

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 the baseline is 3. The description adds fraud-relevant meaning beyond the schema, such as why party defaults to cedente ('è lui che incassa'), why IBAN is collected only for the cedente, and the red-flag rule that a foreign IBAN on an expected Italian supplier is 'il campanello #1 della frode'. These enrich, rather than merely repeat, the 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 opens with a specific verb-resource pair: 'Estrae i dati strutturati da un XML FatturaPA/SDI' and immediately adds the anti-fraud verification performed in the same call. It names the exact checks and distinguishes itself from siblings like parse_fatturapa and verify_payee by combining parsing with verification.

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 clearly states the intended use case ('È la difesa contro la truffa del cambio-IBAN sulle fatture passive') and a key limitation ('NON sostituisce la verifica out-of-band'). It also explains behavior when VIES is down or the budget is exhausted. However, it does not explicitly say when to use this tool instead of parse_fatturapa or verify_payee for standalone needs.

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