Everroad: Utah car dealer facts

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

Annotations already cover read-only, idempotent, non-destructive behavior, and the description adds real value beyond them: missing facts render as 'not stated' and the tool deliberately names no winner, so the agent won't expect a ranking verdict.

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, front-loaded with the count constraint and the returned fields, with no filler; the 'names no winner' caveat sits last where it belongs.

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?

No output schema exists, and the description effectively documents the return contents (hours, weekend sales/service, doc fee, options, Everroad Score with basis) plus missing-data behavior, so an agent can call it confidently; only the provenance of slugs is unstated.

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 the description carries the burden, and it does explain key slug semantics: count must be 2-5 and order is preserved in the output. It doesn't say where slugs come from (presumably find_dealers), a minor 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?

States a specific verb and resource ('Facts for 2 to 5 dealers side by side') and enumerates exactly which facts are returned, which clearly separates it from single-dealer siblings such as dealer_facts and dealer_score.

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 '2 to 5 dealers' bound and 'in the order given' imply the comparing-multiple-dealers use case, but the description never names an alternative (e.g. use dealer_facts for one dealer) or states 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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety needs no restating. The description's real contribution is disclosing the return contents in detail — score scale (0-100), category breakdown, per-metric link, hours by department, doc fee, and per-fact source URL plus checked date — which is meaningful beyond the annotations. It does not say what happens for an unknown/invalid slug or whether results are truncated, keeping it below 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?

A single front-loaded sentence that names the resource first and then lists contents; the parenthetical about slug origin is placed usefully before the payload list. It is dense but nothing is filler; the only cost is a long enumerated run-on that slightly blurs the 'by name' caveat.

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?

No output schema exists, and the description compensates by enumerating the returned fact categories and their provenance metadata (source URL, checked date). With annotations covering the safety profile and the parameter explained, an agent has everything needed to call it correctly; only edge-case behavior is omitted.

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 one parameter and 0% schema description coverage, the description must carry the semantics, and it partially does by explaining the slug comes from find_dealers. But it also claims lookup 'by name' while the schema requires a single 'slug' string with additionalProperties=false and no name field, which is misleading about what can actually be passed.

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 ('every fact on record for one dealer') and enumerates the concrete payload: Everroad Score with category breakdown, hours by department, weekend service, doc fee, service options, plus source URL and checked date. It also names the sibling find_dealers as the origin of the slug, so an agent can distinguish it from dealer_score/compare_dealers without opening a 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?

The phrase 'by slug from find_dealers' implies a two-step workflow (discover, then fetch details), which is a real usage hint. However, it never states when to prefer dealer_score, weekend_hours, fee_law, or compare_dealers instead of this broader fetch, and gives no exclusions or failure conditions. Usage is only implied.

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, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description adds genuine behavioral context beyond that: the score is 0-100, it carries a formula version, it distinguishes measured data from missing dealer-controlled metrics, and it flags which metrics are not on record. It does not cover failure behavior for an unknown slug, which keeps it off 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?

One dense sentence, front-loaded with the resource and then the payload inventory, with no filler. It is long and comma-chained, which pushes reading cost up, but every clause conveys distinct information about what comes back.

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 carries the full burden of describing the return value, and it does so comprehensively — score, band, version, category breakdown, coverage, sources, and gaps. Combined with annotations covering safety and idempotency, an agent has everything needed to call and interpret it.

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% for the single slug parameter, so the description must compensate and it partially does by naming two acceptable sources (find_dealers output or the dealer's name). It never states the expected slug format, casing, or URL convention, and it is unclear whether a raw dealer name is accepted verbatim as a slug.

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 resource (one dealer's Everroad Score) and enumerates exactly what the payload contains: score, band, formula version, per-category points, weight coverage, metric sources, and absent website-controlled metrics. That is far more specific than a restated title. It does not explicitly contrast itself with dealer_facts or compare_dealers, so an agent must infer the boundary from the resource name alone.

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 closing clause tells the agent where the required argument comes from: 'Slug from find_dealers, or the dealer's name,' which effectively routes through a sibling tool. It gives no when-not conditions or explicit alternatives, but the usage context is clear and actionable.

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, closed-world, non-destructive behavior, so the safety profile is covered. The description adds genuinely new behavioral detail by disclosing what comes back — explainer page URLs and the date the sources were checked — which conveys provenance and staleness without an output 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?

A single sentence with no waste, front-loading the subject matter and then the return contents. Every clause carries information the agent cannot get from structured fields.

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 compensates by stating what the response contains (URLs and a checked date), and the zero-parameter schema plus annotations make the invocation profile unambiguous. A brief note on scope (e.g., that this is reference material, not advice, or how it relates to weekend_hours) would complete it.

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?

The tool takes zero parameters, so there is no parameter semantics to document; baseline 4 applies. The description correctly implies the tool is fully self-contained with no input needed.

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 subject (Utah dealer doc fee and the Saturday/Sunday selling rule) and the shape of the return (explainer URLs plus source-check date), so an agent knows exactly what it retrieves. It does not explicitly differentiate itself from the closest sibling, weekend_hours, which likely covers the practical hours question rather than the legal rule.

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 only implied: an agent can infer it should call this when it needs legal background rather than live dealer hours, but the description never says when to prefer it or when to route to weekend_hours or dealer_facts instead. No exclusions or prerequisites are 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 declare readOnly, idempotent, non-destructive and closed-world, so the description only needs to add context — and it does: sort order (county market, then distance from the county reference point, with Salt Lake County anchored at downtown SLC) and the returned fields (page URL and last-checked timestamp). It stops short of covering pagination or the behavior of the `limit` cap.

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 resource and scope, followed by filter detail and then ordering/return behavior. No filler and every clause carries 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?

For a read-only list tool with no output schema, the description supplies return contents and sort order, which is the important missing piece. Remaining gaps are the undocumented `limit` behavior and whether multiple filters combine as AND — minor but real for a five-parameter 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, the description carries the full burden and mostly succeeds: it maps `market` to county market with two sample formats, `make` to manufacturer, `city` to a locality, and enumerates seven concrete values for the otherwise cryptic `attribute` parameter. The `limit` parameter is never explained, leaving one of five parameters opaque.

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 ('List franchise car dealers') plus a clear geographic scope (Utah), which is enough to separate it from siblings like dealer_facts, dealer_score, and compare_dealers. The optional filter dimensions further sharpen what this tool returns.

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 word 'optionally' makes clear that all filters are optional, which implies a browse-all use case, but the description never states when to reach for this tool instead of dealer_score or compare_dealers, nor does it mention any prerequisites. Usage is inferable but not guided.

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, closed-world and non-destructive, so safety is covered. The description adds useful return-content context (numbers plus coverage and method link) that partially substitutes for the missing output schema, but it says nothing about available report inventory, error behavior for bad slugs, or freshness of the published numbers.

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 with no filler; the payload is front-loaded and the example slug follows. The phrasing 'The numbers of a published report' is slightly awkward but costs nothing in length.

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 single-parameter read tool with no output schema, the description should at minimum explain what a 'report' contains and how slugs map to reports. It gestures at both (numbers, coverage, method link, one example) but leaves the report catalog and default behavior unspecified.

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 0% for the single 'slug' parameter, so the description must carry the load. It provides one concrete example value ('utah-weekend-dealer-access') and glosses it as the Weekend Access Report, which is genuinely helpful, but it gives no general slug format, list of valid values, or indication that the parameter is optional and what the default is.

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 says it returns 'the numbers of a published report, with coverage and method link', which is a specific payload, but the naming ('report') and phrasing 'The numbers of a published report' are vague about what kind of numbers (dealer access metrics?) or which report. It never contrasts itself with siblings like dealer_score or compare_dealers, so an agent must infer that this is a static published-report payload rather than computed data.

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?

There is no when-to-use guidance and no alternatives named. The one clue is the parenthetical '(the Weekend Access Report)' tied to the example slug, implying a single currently published report, but nothing states when an agent should call this versus dealer_score or fee_law, nor what happens with an unknown slug.

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, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful domain context, including the Utah rule that dealers may not sell on both Saturday and Sunday, but it does not describe return ordering, pagination, 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?

The description is two sentences, front-loaded with the main resource and scope, and each sentence adds useful information without repetition. 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?

For a simple read-only lookup with two optional filters and no output schema, the description is largely complete: it states what is returned, the optional filters, and a relevant domain constraint. The main minor gap is that it does not explain what the totals contain or how the results are structured.

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 parameter meaning. It identifies both city and market as optional filters, clarifies that the result can be limited to one county market or city, and gives an example market value such as "utah-county".

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 scope: Saturday and Sunday sales and service hours for dealers, optionally filtered by county market or city, plus totals. An agent can tell this is a weekend-hours lookup rather than a general dealer search or comparison.

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 by saying the result can be optionally scoped to one county market or city, but it does not explicitly say when to use this tool instead of siblings like dealer_facts or compare_dealers. There are no when-not conditions or named alternatives.

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