The Used Car Index

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds genuinely useful behavioral context: unknown vehicles return database suggestions, unrated vehicles stay explicitly unrated, and counts reflect source coverage rather than ground truth. The tier-based per-call limit is a valuable operational constraint not present in 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?

Three sentences, front-loaded with the core action and followed by return-behavior caveats and limits. Dense but each sentence carries information; no filler or restatement of the title.

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 does the work of describing return semantics (factual orderings, suggestions for unknown vehicles, explicit unrated status) and the tier limits. It stops short of describing result shape or ordering details, but it is sufficient for an agent to call the tool 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 description coverage is 0%, so structured fields carry no per-parameter meaning. The description clarifies that the input is a set of vehicles and that per-call counts are capped (2 free / 5 paid), but it never explains the required make/model/year triple or the 2000–2027 year window, leaving the schema to define the shape on its own.

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 names a specific verb and resource ('Compare recorded facts for several vehicles side by side') and delineates scope with concrete dimensions (complaints, recalls, verified complaints-per-100k-sold rates). It also explicitly excludes framing ('no recommendation, verdict or safety ranking'), which separates it from the risk-oriented sibling vehicle_risk.

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 context is clear — comparing several vehicles in one call — and hard constraints are stated (free tier up to 2, paid up to 5). It does not explicitly say when to reach for vehicle_risk or recall_changes instead, so the routing guidance against siblings is inferred rather than stated.

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 establish readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: collector status distinguishes an inactive feed from observed events, no photos or dealer text are included, 'delisted' means only that the listing was no longer observed rather than a completed sale, and the tier-based result caps (10 events, no paging on free vs. 200 with cursors on paid). These are exactly the caveats an agent needs before interpreting results.

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 dense sentences, each carrying distinct information: scope and filters, the collector-status caveat, the delisted semantic caveat, and the pagination limits. The most important scoping information is front-loaded and no sentence is 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?

There is no output schema, so the description compensates by enumerating the returned fields (VIN, price, mileage, dates, source, link) and by stating the paging limits. Combined with annotations covering the safety profile, an agent has everything needed to call and interpret this read-only list tool.

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?

With 0% schema description coverage across 9 params, the description has to carry the load, and it largely does: it names the filter axes (vehicle, event type, date) and explains cursor/limit behavior through the paging and per-call caps. It does not spell out the make/model/year breakdown, the default limit of 50, or date format, so a small gap remains.

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 (List) and resource (observed dealer listing changes), enumerates the event types (new, price drop, relisted, delisted), and lists the returned fields. Nothing in the sibling set (compare_vehicles, recall_changes, vehicle_risk) covers listing events, so the tool is trivially distinguishable.

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?

The description implies usage through the filter axes ('filtered by vehicle, event type or date') and the free-tier/paid-tier call limits, which tell the agent when it can and cannot page. However, it never names an alternative tool or states an explicit when-not-to-use condition, leaving the agent to infer selection.

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 readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description adds real behavioral context beyond that: daily-refresh cadence, free-tier cap of 10 with no paging versus paid 200 with cursors, the presence of a vehicle watchlist, the fields returned per change, and an explicit 'published records, not prediction or advice' disclaimer. It stops short of covering auth requirements or error behavior.

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 dense sentences, front-loaded with what the tool returns before moving to filters, record contents and tier limits. Each sentence carries distinct information, though the middle block is information-heavy enough that a bulleted filter list would scan faster.

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 an 8-parameter, zero-coverage, no-output-schema tool this is close to complete: filters, ordering, returned fields, freshness and paging limits are all present. Minor gaps remain around default values and date-format conventions that an agent must otherwise read out of the raw 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?

Schema description coverage is 0%, so the description carries the burden and largely does: it names make, model, model year, type (with all three enum values) and observed date as filters, and the paging caps implicitly explain 'limit' and 'cursor'. It never explicitly documents the default limit of 50, the YYYY-MM-DD format of since/until, or that cursor is an opaque token, so it does not fully compensate for the coverage gap.

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 gives a specific verb ('List') and a well-scoped resource ('new and updated NHTSA recalls, investigations and complaint-count changes'), including ordering ('newest first') and origin (daily NHTSA bulk-file comparison). It does not, however, explicitly distinguish itself from the similarly named sibling 'listing_changes', leaving the agent to infer the boundary.

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 implied rather than stated: the filter list (make, model, model year, type, observed date) tells the agent what kinds of queries this tool answers, and the tier note warns about result caps. There is no explicit when-to-use/when-not guidance and no routing to or away from 'compare_vehicles', 'listing_changes' or 'vehicle_risk'.

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?

Beyond the annotations (readOnly, idempotent, openWorld=false), the description discloses substantive behavior: spellings and aliases resolve to the stored vehicle, a zero is confirmed only when coverage_complete is true, Jev tags cover only MY2012+ and ~43% of complaints, and per-label confidence is not accuracy. It also explicitly disclaims what the data is not (prediction, safety rating, verdict, repair advice, individual vehicle history), which prevents misuse.

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 core purpose and returned record families are front-loaded in the first sentence, and the caveats follow in a logical order. It is dense and somewhat long, with a couple of run-on sentences, but every clause carries information an agent needs.

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 must describe the return payload, and it does: it lists the record types, the optional verified rate, source coverage, and the coverage_complete flag that governs whether a zero is meaningful. Combined with the Jev-tag caveats, an agent has enough to call the tool and interpret the result without surprises.

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 0%, so the description must carry the parameter burden. It names the three inputs and adds genuine meaning for make/model ('spellings and aliases resolve to the stored vehicle'), but says nothing about the year parameter's bounds or format, leaving one of three parameters semantically unexplained.

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 opens with a specific verb and resource: 'Look up the recorded risk facts for one make, model and model year,' then enumerates the exact record families returned (complaint counts by system/subsystem, recalls, investigations, manufacturer communications, rate, coverage). It is clearly a single-vehicle record lookup, which separates it from compare_vehicles, listing_changes and recall_changes.

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 implied rather than stated: the 'one make, model and model year' framing tells the agent this is a single-vehicle lookup, but there is no explicit when-to-use this vs. compare_vehicles or the change-tracking siblings. No prerequisites or exclusion conditions are given.

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