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

The description goes well beyond the readOnlyHint and openWorldHint annotations. It discloses the three-way result (valid/invalid/unavailable), explains that outages are never reported as false invalid, notes the Ed25519 signature and provenance[] field with real consultation dates, and explicitly states the payment model and price. This is rich behavioral context that helps an agent set expectations correctly.

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 purpose and usage context before moving into return behavior, security properties, and payment. It is a bit dense and includes some redundancy with the title ('VAT number check against VIES'), but every major clause adds operational value and no filler is present.

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 tool with an output schema and basic annotations, the description is fully complete for selection and invocation: it covers purpose, usage context, result semantics, outage behavior, proof/provenance, and payment requirements. Nothing an agent needs to decide whether to call it or handle its response is missing.

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 schema already documents vat_number, api_key, and x_payment. The description adds meaningful extra context beyond the schema, such as the specific x402 price ($0.003 in USDC or EURC), the distinction between prepaid credits and signed payment, and the guarantee that unavailable VIES results are never fabricated. This lifts the score to 4.

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 phrase, 'VAT number check against VIES,' and clearly identifies the resource and scope: validating any EU intra-community VAT number against the official VIES service. It also distinguishes this tool's narrow purpose by stating it covers 'the tax half of verifying a supplier before payment,' contrasting with broader verification workflows.

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 explicitly says when to use the tool: when only the tax half of supplier verification is needed, before invoicing, applying reverse charge, or paying. It also cites concrete regulatory mandates in France and Belgium. However, it does not name a specific alternative tool or state a 'when not to use' condition beyond the implied 'only need the tax half' phrasing.

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