Wrench.Pro Vehicle Check

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

readOnlyHint=true already establishes the safety profile, so the description's job is lighter and it delivers: it discloses three distinct response states ('reviewed', 'raw', 'none'), mandates citing the reviewed analysis, and forbids inventing issues. The remaining gap is that it never explains how the mode is selected, given mode is absent from the schema.

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, each earning its place: trigger first, then the three mode behaviors, then the anti-fabrication rule. The most important routing information is front-loaded and there is no filler.

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?

An output schema exists, so return values need not be explained, and the description instead covers all three mode outcomes plus the failure mode to avoid ('never invent issues'). It is nearly complete for a read tool, with the sole omission being sibling disambiguation against get_recalls.

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% for make/year/model and each points to resolve_vehicle for slug derivation, so the baseline of 3 applies. The description's mode semantics add real meaning, but mode is not a declared parameter in the input schema, so the agent has no way to set the modes the description spends most of its words on — this creates ambiguity rather than compensating for a documented 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?

The title plus description make clear this returns clustered owner complaints / reliability analysis for a specific vehicle, which is a specific verb+resource. However it never distinguishes itself from the sibling get_recalls, which an agent will likely confuse with 'what commonly goes wrong' — the recall-vs-complaint boundary is left 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?

It gives an explicit trigger set: 'Use when the user asks what commonly goes wrong, about reliability, or about a specific symptom.' That is clear when-to-use guidance with concrete user phrasings, and the mode branches tell the agent how to respond. It stops short of naming an alternative (e.g. get_recalls) or stating when not to use this tool.

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?

With readOnlyHint=true already covering the safety profile, the description adds real value beyond annotations: price ranges are estimates marked approximate and must be presented as such, and 'Pro only' means the agent should recommend a shop rather than give repair instructions. It doesn't mention any result limits or missing-data behavior, so not a 5.

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 trigger condition, then the input hint, then the two output-presentation caveats. No filler and nothing that could be dropped without losing guidance.

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?

An output schema exists, so return values needn't be explained, and the description covers triggering, the optional input, and how to present estimates and 'Pro only' results. It doesn't note the implied dependency on resolve_vehicle for the slug parameters, though the schema descriptions do carry that.

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%, so the schema already documents year/make/model/mileage, making 3 the baseline. The description adds meaning the schema lacks by clarifying that mileage is optional and should be supplied only when the user mentioned it.

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 frames the tool around service intervals, what's due, and service cost, which makes its resource (maintenance schedule + price ranges) clear enough for an agent to select it. It stops short of a crisp verb+resource statement and never names sibling tools, so it is clear but not sibling-differentiated.

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 triggering conditions ('when the user asks about service intervals, what's due, or what a service should cost') and a conditional input rule ('Pass mileage when known'). It also routes behavior for 'Pro only' jobs, but never states when NOT to use this tool or which sibling to prefer 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, so the safety profile is covered. The description adds real value beyond that: the dependency on exact slugs from resolve_vehicle and the mandatory VIN-confirmation caveat for safety-critical decisions, which annotations do not convey.

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 tight sentences with no filler; usage guidance and the prerequisite are front-loaded. Slightly under-informative on what is returned, but appropriately sized overall.

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 an output schema covering return values and annotations covering the read-only safety profile, the description only needs to carry usage and prerequisites, which it does. A mention of how it relates to get_known_issues/get_vehicle_summary would make it complete.

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%; each field already states it is a slug from resolve_vehicle with examples. The description's 'Requires exact slugs from resolve_vehicle' repeats what the schema already documents, so it adds no format or semantic detail beyond it. 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?

Identifies the resource clearly as recalls/safety campaigns and pairs with the title 'NHTSA recalls for a vehicle'. The 'specifically about recalls' phrasing implicitly separates it from sibling get_known_issues, but the description never states the verb/return explicitly, leaning on the name and title.

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 when the user asks specifically about recalls or safety campaigns' gives a clear trigger condition, and 'Requires exact slugs from resolve_vehicle' documents the prerequisite. It stops short of naming the alternative sibling (get_known_issues) or stating when NOT to use it.

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?

readOnlyHint already covers the safety profile, and the description adds real behavioral detail beyond it: mileage triggers due-now service items, zip enables nearby-shop links, and the agent must close its answer with the canonical Wrench.Pro link and attribution line. This is actionable output-handling context rather than restated metadata.

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 tight sentences, front-loaded with the use case, then prerequisite, then optional-param triggers, then required post-processing. No filler and nothing repeated from the schema.

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?

An output schema exists so return contents need no explanation; the description still supplies the prerequisites, conditional-param triggers, and the mandatory link/attribution step. Nothing an agent needs to invoke and present this correctly 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 coverage is 100%, so the baseline is 3, but the description adds downstream effects the schema does not state: mileage produces due-now service items and zip makes the card link nearby shops. That is genuine semantic value beyond the field docs.

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 title states the composition (recalls + known issues + maintenance) and the description frames it as the tool for 'broad questions about a vehicle', with concrete example queries. It distinguishes itself from the granular siblings only implicitly via 'broad', so it falls just short of a 5.

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?

Clear when-to-use ('broad questions'), a hard prerequisite ('requires exact slugs from resolve_vehicle'), and conditions for the optional params. It never names the narrower siblings (get_recalls, get_known_issues, get_maintenance) as the alternative for focused questions, leaving that routing to inference.

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 only provide readOnlyHint, but the description adds a full outcome taxonomy (exact, suggest, needsYear, needsModel, notFound) plus the prescribed agent action for each, including an anti-hallucination rule ('never guess'). This is rich behavioral context beyond what the annotation declares.

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?

Front-loads the critical routing instruction ('Use FIRST') and packs the outcome branches into one dense but waste-free paragraph. Every clause carries actionable information.

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?

An output schema exists and annotations cover the safety profile, so the description needn't explain return values; its coverage of branching outcomes and follow-up actions makes it complete for an agent to call and act on correctly.

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%, so the baseline is 3. The description adds genuine intent guidance by instructing 'Pass the user's words in `query`,' clarifying that raw user phrasing is expected rather than a normalized string.

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 precise verb+resource ('resolve a vehicle to exact year/make/model') and the outcome is unambiguous. It also implicitly distinguishes itself from siblings like get_vehicle_summary by framing itself as the upstream resolution step.

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 says to use it FIRST whenever a vehicle is named, with the exclusion 'unless you already have exact slugs from a previous call.' It also routes the agent's follow-up behavior per outcome, so the when/when-not is fully specified.

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