UK Data: VAT number checks

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuinely new context: the authoritative data source (official HMRC register), the return payload (business name and address), and a per-call cost of 2 credits, which matters for agent budgeting.

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 short sentences: the first front-loads the action, source and return value; the second carries usage context and cost. Nothing is redundant or buried.

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 single-parameter lookup with no output schema, the description covers what the tool does, where the data comes from, what comes back and what it costs. It stops short of describing failure behavior (e.g., unregistered or malformed VAT numbers), which would complete the picture.

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 single parameter already documents the '9 or 12 digit' format. The description adds no format, normalization or edge-case guidance beyond the schema, 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?

The description opens with a specific verb and resource ('Validate a UK VAT registration number against the official HMRC register') and states what is returned (business name and address). The 'UK' qualifier distinguishes it from generic VAT siblings like 'vat' and 'vat_check', though it never names them explicitly.

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?

'For invoicing, supplier checks and VAT reclaim' gives use-case context that implies when to reach for it. However, there is no explicit when-not guidance and no reference to the sibling VAT tools, so the agent must infer which VAT tool applies to non-UK numbers.

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

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely new behavioral facts: the authoritative upstream per region (VIES vs HMRC) and a cost of 2 credits, both of which affect an agent's decision to call. It stops short of saying what happens on an invalid number or a service outage.

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 action and result, then source, then use cases, then format. Nothing is padded, though the examples sentence is close to redundant given the schema already states prefixes are optional.

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 read-only lookup with no output schema, the description usefully names the returned fields and the regional data sources. The main omission is failure semantics — whether an unregistered number returns a negative result or an error — which matters for a validation tool.

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%, so both parameters are already documented, including that the prefix is optional. The worked examples (IE6388047V, DE811234567, GB553557881) make the accepted format concrete, but this largely restates the schema rather than adding new meaning.

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 states a specific verb and resource ('Validate a VAT number') plus the return payload (registered business name and address) and the two upstream sources (VIES for EU, HMRC for UK). It does not differentiate from the near-identical siblings 'uk_vat_check' and 'vat', so an agent cannot tell from the description alone which of the three to pick.

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 lists concrete use scenarios (invoicing, supplier onboarding, tax and KYB checks), which gives real context for when to reach for it. However, it never names an alternative or an exclusion, and with siblings called 'uk_vat_check' and 'vat' present, the absence of routing guidance is a clear gap.

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