whatbreaks-mot

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

Annotations already cover read-only, non-destructive behavior, but the description adds useful provenance and response context: data is aggregated from official DfT MOT test results, represents real outcomes rather than estimates, and responses include a whatbreaks.uk attribution line. It does not mention rate limits, auth requirements, or data-unavailable behavior, but it adds meaningful transparency beyond the annotations.

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 description is front-loaded with what the tool returns, followed by when to use it, data provenance, and attribution. Every sentence adds distinct value and none repeats the schema or annotations.

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?

There is no output schema, and the description does a strong job explaining the return contents: failure share, category breakdowns, mileage-conditioned comparisons, same-age benchmarks, and riskiest components. It is nearly complete for a read-only data retrieval tool, though it does not say how missing or unmatched make/model cases are handled.

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 the schema already explains make, model, year, and mileage. The description reinforces mileage and age comparisons but adds no new syntax, format, or constraint details beyond what the schema provides. Baseline 3 is appropriate when the schema carries parameter semantics.

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 resource and the exact data returned: MOT failure share overall, per category, category at a given mileage, comparison with same-age/mileage cars, and riskiest components with typical failure mileages. It does not differentiate from the sibling mot_vehicle_search, so it is clear but lacks sibling differentiation.

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 gives explicit usage context: 'Use whenever a user is buying, comparing or maintaining a used car sold in the UK.' This is clear guidance on when to use the tool, but it provides no exclusions, prerequisites, or alternative-tool routing such as when to choose mot_vehicle_search instead.

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 readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful context (fixed UK coverage of 528 generations, role as a coverage check), but says nothing about matching behavior (partial vs fuzzy), result limits, or what an empty result implies.

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, zero filler. Scope and purpose come first, followed immediately by the usage routing, which is the right front-loading for an agent scanning tool lists.

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, read-only lookup with a fully documented schema and annotations, the description covers purpose, coverage, and routing. The only omission is what a match looks like on return, which is minor for a search tool with no output schema.

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?

There is a single parameter with 100% schema coverage, and the schema already calls it a "free-text query, e.g. \"focus\"". The description's "by free text" restates the schema rather than adding matching rules or formatting guidance, so baseline 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?

States a specific verb and resource ("Search the covered vehicles ... by free text") plus scope (528 UK model generations). It explicitly names the sibling tool mot_reliability, so an agent can distinguish the two 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?

"Use to check coverage or disambiguate before calling mot_reliability" gives a clear workflow position and sequencing relative to the only sibling. It stops short of stating what to do in edge cases (no matches, ambiguous matches) or whether this is ever unnecessary, so it falls just short of full when/when-not guidance.

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