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

Annotations are all false hints, so the description carries the full burden and delivers. It discloses dependence on VIES availability and member-state data, clarifies that a valid VAT number does not prove solvency or absence of fraud, and — critically for a paid tool — explains that a successful invocation consumes x402 payment while the challenge is free and repeat calls may require new payment. This resolves the ambiguity of readOnlyHint=false by clarifying source records are not modified but money can be spent.

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 well-organized with labeled sections (Use when, Avoid when, Limitations, Price, Paid-call behavior, Accepted networks) that make it easy for an agent to scan, and the core purpose is front-loaded. It earns its length, though the 'Use when' section repeats the invoicing/onboarding context in two nearly identical sentences.

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 paid, externally-dependent validation tool, the description covers everything: purpose, trigger conditions, exclusions with named alternatives, limitations, price, payment-consumption behavior, accepted networks, and input prerequisites. An output schema exists for return values, and the 'explicit unavailable status' even previews the response shape, so nothing an agent needs to invoke this correctly 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 description coverage is 100% — all three parameters (vat_number, country_code, number) are documented with patterns, enum, and their relationship, including the anyOf constraint. The description merely restates the either/or input requirement ('You have either a complete VAT number or a country code plus national number'), adding no semantic detail beyond the schema, so baseline 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?

The lead sentence states a specific verb and resource — 'Validates an EU VAT number through the European Commission VIES service' — and adds a distinguishing behavioral detail ('with explicit unavailable status'). It is clearly differentiated from the company_fr_* siblings by explicitly naming invoice-check and supplier-verification as the tools for French-company checks.

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 'Use when' and 'Avoid when' sections give concrete trigger conditions (before invoicing or supplier onboarding) and name precise alternatives: company/fr/invoice-check for French invoice consistency and company/fr/supplier-verification for broader compliance or IBAN checks. Nothing is left to inference.

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