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

Annotations already establish readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered; the description adds genuinely new context on top, namely the upstream data sources (DVSA, DVLA, HPI) and the hard coverage boundary (GB/NI only, other countries will not be found). It stops short of noting any rate limiting or failure modes for unknown plates, which would have pushed it higher.

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 important constraint (UK-only) is front-loaded, followed by sources, returned fields, and routing cues in a logical order. The seven-phrase example list is longer than strictly necessary but earns part of its space as query-matching vocabulary; the last set of quoted examples could be trimmed.

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?

With no output schema, the description correctly compensates by enumerating the returned fields, and it covers scope, data provenance, and invocation triggers. The one remaining gap for a tool that sits beside two MOT-focused siblings is the absence of a handoff rule telling the agent when to prefer get_mot_history or get_mot_status.

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% and the registration parameter is already richly documented (spaces/case do not matter, GB or NI only), so the baseline is 3. The description adds synonym coverage ('number plate, reg, registration') and the 'UK-registered vehicles only' constraint at tool level, which helps the agent map informal user phrasing onto the single parameter.

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?

It names a specific verb and resource ('look up a UK number plate') and enumerates exactly what comes back: make, model, colour, year, fuel type, age, MOT validity/expiry, and tax status/due date. It also frames itself as 'the best first call for any general question', which implies a division of labour with its MOT-specific siblings, but it never names get_mot_status or get_mot_history, so the differentiation stays implicit.

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?

Usage is well signposted with seven concrete trigger phrasings ('what car is wr25vup', 'is it taxed', 'is it road legal'), giving the agent strong positive context for when to invoke it. What's missing is the negative case: there is no statement that detailed MOT test records or a narrow MOT-status check should be routed to get_mot_history or get_mot_status instead, despite significant field overlap.

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