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

Annotations already establish read-only/idempotent/open-world safety, so the description's job is added context — and it delivers: 'real-time' signals a live call with no caching, and the Spain/withheld_by_member_state null-name behavior is a non-obvious failure mode an agent would otherwise misread as a bad VAT number. That is exactly the kind of quirk annotations cannot express.

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?

Two sentences, no filler. The core capability leads, the return shape follows inline, and the caveat plus its remediation land last — the front-loading order matches how an agent reads a definition.

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?

An output schema exists, so the description is not obliged to enumerate return values, yet it names the key ones cheaply. Combined with the withheld-disclosure edge case and the sibling handoff, everything needed to call this correctly and interpret a null result is present.

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% and the schema already documents q and its vat/query aliases with format examples (ESA28015865, IE6388047V), so the description correctly does not repeat them. It adds marginal value by naming vat_number among the returned fields, which loosely connects the input to output, but it adds no input syntax or constraint detail beyond 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?

States a specific action and resource ('Real-time EU VAT validation via VIES') with the scope (27 EU countries) pinned down. It also separates itself from the sibling entity_lookup by assigning that tool the registered-name use case, so an agent can discriminate without opening either schema.

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?

Gives a clear routing rule: if name/address come back null with name_disclosure=withheld_by_member_state, use entity_lookup instead. That is concrete when-else guidance rather than vague context, but it only covers the fallback path — there is no explicit statement of when verify_vat should not be used (e.g. non-EU VAT or already-cached lookups).

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