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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-redundant behavior: an explicit cost of 10 credits, the authoritative source (DVSA MOT records), and two coverage limits. Missing is anything about rate limiting, error behavior for unknown plates, or result freshness.

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?

Three sentences, no filler, front-loaded with the core capability before the field list, then caveats last. Every clause carries information, including the parenthetical cost.

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 read-only lookup with no output schema, the description does the heavy lifting well by enumerating returned fields and flagging the two data-availability caveats. It could go one step further by noting what a failed/unknown-plate response looks like or how the history flag changes the payload size, but nothing essential to correct invocation 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% with only two parameters, so the schema already documents both `plate` and `history` (including the default). The description's mention of "the full MOT test history" loosely gestures at the history flag but adds no format or example beyond the schema's own "AB12 CDE" example. Baseline 3 is appropriate.

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?

Names a specific verb and resource (UK number plate lookup) and enumerates exactly what comes back: make, model, colour, fuel, engine size, registration date, MOT expiry, recall flag, mileage, and full MOT history. That level of specificity is well above a restatement of the name. It stops short of a 5 because it does not differentiate itself from near-overlapping siblings such as uk_mot_history, uk_mileage_check, or vin_decode, which an agent would need to disambiguate.

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?

Scope exclusions are given ("Does not include road tax status", "Cars under 3 years old have no MOT history yet"), which usefully tell the agent when results will be thin. However, there is no guidance on when to pick this tool over the sibling tools that overlap on MOT history and mileage, and no statement of alternatives. Usage is implied by the field list rather than directed.

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