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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description's added value is the trust boundary: the result is a format/checksum verdict, not a registration confirmation. That is exactly the caveat an agent needs before reporting an outcome to a user; it doesn't discuss failure modes for malformed input, but the gap is modest.

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, with the capability stated first and the scope limitation second. Every clause earns its place.

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 one-parameter boolean-style checker with full schema coverage and annotations carrying the safety profile, this is nearly complete. The one omission is any statement of the return value (valid/invalid plus reason), which no output schema supplies, though the result shape is largely predictable for this kind of 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 coverage is 100% and the schema already documents the single parameter including the optional "GB" prefix. The description nonetheless adds accepted input shapes (9 digits, 12 with a branch, GD/HA prefixes), which tells the agent what counts as well-formed input beyond the type declaration.

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 verb ("Check") and resource ("UK VAT number") plus exactly what is validated: format and check digits. It does not name the nearest sibling (vat_calculator, which computes VAT amounts), so an agent must infer the distinction from the tool names alone.

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?

Explicitly bounds the scope with "Does not confirm registration; HMRC's service does." That is a real when-not condition that prevents misuse as an authoritative validator. It stops short of naming a sibling alternative, but the exclusion is clear enough to route the call correctly.

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