Wrench.Pro Vehicle Check

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

With no annotations, the description carries the full burden and does substantial work: it defines what 'reviewed', 'raw', and 'none' mean, tells the agent to cite reviewed analysis, instructs it to surface rawTopComponents on unreviewed data, and forbids fabricating issues. It omits auth requirements, but for a read-only vehicle lookup that is a minor gap.

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 trigger is front-loaded, followed by compact mode-by-mode handling and a closing guardrail ('Never invent issues') — every sentence drives agent behavior. The telegraphic style ('is Wrench.Pro's human-reviewed analysis') is dense but not padded.

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 shapes need not be spelled out, and the description instead supplies the interpretation rules an agent needs for each mode plus an anti-hallucination instruction. What is missing is only the relationship to sibling tools like get_recalls, which would help an agent disambiguate reliability vs. safety-recall queries.

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 all three required parameters (year, make, model) are documented with resolve_vehicle provenance, so the schema already does the heavy lifting. The description adds no syntax or format detail for these inputs; the mode values it discusses appear to be response fields rather than input parameters, which is baseline-3 territory.

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 is framed as a trigger ('Use when the user asks what commonly goes wrong, about reliability, or about a specific symptom'), which implies the resource is known-issue/complaint data, and the mode semantics make clear what is returned. It stops short of explicitly stating the verb+resource ('returns known issues for a vehicle') and never names get_recalls as the sibling it is not, so an agent must infer the boundary from the domain wording.

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 a concrete when-to-use trigger covering reliability questions and symptom questions, and prescribes handling for each mode ('reviewed' = cite it; 'raw' = say no reviewed issues and present rawTopComponents; 'none' = say no complaint data). There is no explicit when-not or alternative-tool routing, which keeps it out of 5 territory.

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 no annotations, the description carries the full burden and does well: it discloses that ranges are estimates that must be presented as approximate, and that 'Pro only' means the job isn't realistic DIY. It doesn't detail authentication, rate limits, or output format, but the output schema exists to cover return values.

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 sentences, each earning its place: usage trigger, mileage instruction, presentation guidance, and output framing for 'Pro only'. Front-loaded with the usage condition.

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?

Given an output schema exists, the description needn't explain return values. It covers when to use, mileage handling, and output presentation. It could mention prerequisites (e.g., needing resolved vehicle identifiers), though the schema descriptions reference 'from resolve_vehicle' which implies this. Nearly 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 coverage is 100%, so the schema already documents all parameters including the mileage constraint (0-1,000,000). The description adds 'Pass mileage when known,' which reiterates the schema's 'when the user mentioned it' – marginal added value. Baseline 3 is appropriate when the schema does the heavy lifting.

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 and description clearly establish this as a maintenance schedule tool with Dealer/Shop/DIY price ranges and service intervals. It states a specific resource (maintenance schedules) but doesn't explicitly differentiate from siblings like get_known_issues or get_recalls, though the distinct purpose is inferable.

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 states when to use ('when the user asks about service intervals, what's due, or what a service should cost') and provides concrete conditions for mileage input ('Pass mileage when known'). Also includes specific guidance on handling 'Pro only' jobs, which routes the agent's response behavior.

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 no annotations, the description carries the full disclosure burden and delivers an unusual, high-value behavioral instruction: always direct the user to verify against their own VIN at nhtsa.gov/recalls before acting. It does not disclose read-only status, data source currency, or rate limits, but the safety disclaimer is substantive context beyond any structured field.

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 short sentences, each load-bearing: the trigger condition first, the resolve_vehicle dependency second, the mandatory safety caveat last. No filler and front-loaded with the usage cue.

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 described, and the description covers the trigger and prerequisite. Its only gap is behavioral disclosure (read-only nature, data freshness) that would matter more given the absence of annotations.

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 states each field is a slug from resolve_vehicle with examples, so the description's mention of exact slugs largely repeats structured data. Baseline 3 is appropriate since the schema does the heavy lifting.

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 makes clear this retrieves recalls/safety campaigns for a vehicle, and the phrase 'asks specifically about recalls' implicitly contrasts with the broader sibling get_known_issues. It stops short of an explicit verb+resource statement or naming the sibling it excludes, so it is clear but not maximally 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 a concrete triggering condition ('when the user asks specifically about recalls or safety campaigns') and a prerequisite ('requires exact slugs from resolve_vehicle'), which routes the agent to resolve_vehicle first. It does not state when NOT to use it or contrast it directly with get_known_issues.

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 no annotations, the description carries the full burden, and it does add real behavioral context: a hard prerequisite (exact slugs from resolve_vehicle) and a required post-answer action (end with the canonical Wrench.Pro link and attribution line). It does not disclose permissions, read-only nature, or rate limits, but the added prerequisite and output requirement are meaningful beyond the structured fields.

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 sentences, front-loaded with the usage trigger, then prerequisites, then conditional parameters, then output requirement. Every sentence carries information; no padding or repetition.

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. The description covers when to use it, the slug prerequisite, conditional optional-param behavior, and required output formatting, which is everything an agent needs to invoke it 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, but the description adds effect-level meaning: mileage yields 'due-now service items' and zip enables 'nearby shops' links. That explains what each optional parameter actually does, exceeding the schema's plain descriptions.

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 clear use case (broad vehicle questions) and the title establishes it as the aggregated report covering recalls, issues, and maintenance. It does not explicitly name the sibling tools (get_recalls, get_known_issues, get_maintenance) it supersedes, so the differentiation is implied rather than stated.

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?

Strong conditional guidance: it says to use this for broad questions with concrete example phrasings, and specifies exactly when to pass mileage (user mentioned odometer) and zip (user mentioned a ZIP code). It stops short of naming the narrow sibling tools as the alternative for targeted lookups.

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 no annotations, the description carries the full behavioral burden and largely does so: it enumerates the return states (exact, suggest, needsYear, needsModel, notFound) and prescribes the agent action for each, including 'ask ONE question listing availableYears' and 'never guess'. The only borderline gap is that some of this return-state detail may overlap the output schema, but the action protocol (confirm, ask one question, decline) is genuine added value.

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 call-order rule is front-loaded in the first clause, and every subsequent clause does work: input routing, then the return-state handling. The quoted examples add a little length but earn their place by illustrating real user input forms.

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 the return shape need not be re-explained, and the description still supplies the behavioral handling for each return state. For a resolution/normalization gate feeding four sibling lookup tools, nothing an agent needs to call it 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 all four parameters are already documented, establishing a baseline of 3. The description adds only a thin clarification ('Pass the user's words in query'), which does resolve the choice between the free-text query and the structured make/year/model fields, but adds no format or precedence detail beyond that.

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 conveys a specific function: it takes a user-spoken vehicle and returns resolvable slugs, with an explicit call-order instruction ('Use FIRST whenever the user names a vehicle'). It doesn't state the resolution verb outright in one sentence, but the returns clause ('use the returned slugs') makes the purpose unambiguous and clearly distinct from the lookup siblings (get_vehicle_summary, get_recalls, etc.) that presumably consume slugs.

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 when ('whenever the user names a vehicle') and an explicit when-not ('unless you already have exact slugs from a previous call'), which is exactly the alternative-condition routing an agent needs. It also provides lexical triggers ('2017 Ford Escape', '17 F150', 'my Honda Civic') that cover common user phrasings.

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