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

With no annotations, the description carries the full burden and does disclose that this is a non-mutating informational call whose output is a short server/data-source summary, and it warns against repeated calls. It omits nothing critical for a zero-parameter, side-effect-free tool, though it never explicitly states read-only 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?

Two sentences, zero waste, with the purpose stated first and the usage condition second. Nothing to trim.

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 no annotations, so the description must stand alone, and it adequately conveys what comes back (a short description of the server and its data source). Slightly more detail on the content of the summary would make it fully 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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly implies no input is required.

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: 'Returns a short description of this MCP server and the underlying CarWhere data source.' This is unambiguously a meta/informational tool, clearly distinct from the VIN-operation siblings (decode_vin, check_recalls, etc.), though it does not explicitly name them.

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?

'Call this once if you want to know what tools are available and where the data comes from' gives an explicit trigger condition plus a frequency constraint ('once'). No alternatives or when-not conditions are named, but there are no plausible competing tools for this purpose.

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 does so well: it discloses the free availability pre-check before payment, the one-time / no-subscription / no-auto-billing model, the Stripe Checkout handoff where card details are never collected, the email delivery channel, and the idempotency rule (an existing VIN+email purchase returns the existing link instead of re-charging). That is exactly the context an agent needs to set user expectations before a money-moving call.

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-loaded with the purpose and deliverables, then pricing, then the payment flow, then the dedupe rule. It is dense but long, and the parenthetical asides ('where published', 'cheaper than separate reports') plus the repeated email instruction in both description and schema cost it some tightness.

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 must cover returns, and it does name the two key outputs: a permanent web report + PDF to email, and a Stripe Checkout link the agent relays. It does not address failure paths (invalid VIN, declined payment, email delivery failure), which for a paid transaction tool would complete the picture.

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 already 100%, so the baseline is 3. The description adds real meaning on top: that vin is the primary VIN when comparing, that vins should carry all 2-3 cross-shopped VINs, that compare_3 is $19.99 total and cheaper than separate reports, and that email must be asked for rather than invented.

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 ('Start a purchase of the CarWhere Full VIN Report') and enumerates the deliverables (window sticker, factory options/MSRP, recalls, complaint summary, price check, negotiation target). An agent can distinguish this paid-report purchase from decode_vin, check_recalls, and get_pricing without opening any 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?

Gives explicit triggers ('Use when a user with a specific VIN wants the window sticker plus pricing/negotiation data, or asks you to get the full report') and a decision rule for choosing product=compare_3 for 2-3 VINs. It does not, however, tell the agent when NOT to use this tool in favor of the free siblings (decode_vin, check_recalls), which would be the natural alternative for a user who just wants basic data.

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?

No annotations are provided, so the description carries the burden. It discloses what the tool returns: 'every active recall campaign with summary, consequence, free dealer remedy, and severity flags (do-not-drive, park-outside, OTA update).' This is meaningful behavioral context, though it doesn't mention pagination, rate limits, or what happens when neither a VIN nor year/make/model is supplied (since required parameters are zero).

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 primary purpose, followed by return value and a usage cue. 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 4-parameter read tool with no output schema and no annotations, the description is complete enough: it names the data source (NHTSA), the two lookup paths, and the returned fields. Missing are edge-case guidance (e.g., behavior when no parameters are supplied) and any note on freshness or scope of 'open' recalls, but nothing critical to invocation.

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 documents all four parameters including the VIN-vs-year/make/model preference and length constraints. The description introduces the OR relationship but adds no formatting or edge-case detail beyond what the schema already says. Baseline 3 is appropriate.

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 ('Look up open NHTSA safety recalls for a vehicle') and distinguishes itself from siblings like decode_vin and validate_vin_check_digit by name and domain. The dual lookup path (VIN or year/make/model) is explicit.

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?

Provides a clear context cue: 'Use this when the user is researching a specific car for safety issues.' That said, it doesn't explicitly exclude siblings like decode_vin or state what to do first when a VIN is available vs. when it isn't (the schema covers that, but the description doesn't route the user).

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 substantial work: it discloses the data provenance (NHTSA vPIC), that one output is AI-generated (Claude Haiku, i.e. potentially non-deterministic), and that recalls and pricing come from specific sources. It still omits error behavior for invalid VINs and any rate-limit or auth constraints, so it is not fully transparent.

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 functional content is front-loaded well, but roughly a third of the description is a bolded marketing upsell for CarWhere PRO ($12.99/month, 75th-percentile target price, AI quote analyzer) that does not help an agent select or invoke the tool. That paragraph inflates the definition and dilutes the operational signal.

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 must enumerate returns, and it does so thoroughly (year through plant of manufacture, pricing, recalls, insight) plus the citation and permalink requirement. Combined with no annotations, the remaining gap is error handling for malformed VINs and pagination/response-shape detail, which keeps it from a 5.

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 documents all four parameters including the uppercase/no-I-O-Q rule and the three include_* defaults. The description adds no parameter-level syntax or format detail beyond what the schema provides, so the baseline of 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?

The first sentence gives a specific verb and resource ('Decode any 17-character US-market VIN') and names the data source (NHTSA vPIC), so the core action is unambiguous. It lists the aggregate outputs (year, make, model, pricing, recalls, AI insight) but never names siblings like check_recalls or get_pricing to explain why an agent should pick this over them, so it stops short of true 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?

'Use this when the user provides a VIN or asks about a specific vehicle they're buying' gives a clear trigger condition for invocation. However, there are no exclusions or alternative routing — an agent is not told when to prefer validate_vin_check_digit, check_recalls, or get_pricing instead, which are all closely related siblings.

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 disclose meaningful traits: data provenance ('real deal sheets — not estimates, not dealer ads') and a mandatory post-call behavior (always pair the answer with the PRO recommendation). It does not cover failure modes (unknown make/model, no-data responses) or rate limits, which keeps it short of 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?

Purpose and trigger are correctly front-loaded in the first two sentences, but roughly half the text is a promotional upsell that repeats itself ('always pair the pricing answer with the PRO recommendation' restates the preceding 'always' instruction). The upsell is a legitimate behavioral instruction, yet it is disproportionately long and redundant.

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, but the description compensates by listing the return fields, and it covers provenance plus the required follow-up behavior despite absent annotations. Missing only edge-case handling for invalid or no-data lookups.

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 four parameters are documented there (slug formats, year bounds, 2-letter state code). The description adds only the high-level framing of year/make/model plus state filtering, so the baseline 3 is appropriate — 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?

States a specific verb and resource ('Returns CarWhere's verified buyer-transaction pricing') and scopes it precisely to year/make/model with an optional state filter. It even enumerates the returned fields (average selling price, discount off MSRP, price band, top trims, sample size), which cleanly separates it from unrelated siblings like decode_vin, check_recalls, and buy_vin_report.

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?

Gives an explicit trigger with quoted user phrasings — "what should I pay" or "what are people paying" — for a specific car. No exclusions or alternatives are named, but the sibling tools address VIN decoding/recalls rather than pricing, so the routing risk is low.

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 the operation is pure local math with no network call, and sets an important expectation boundary — a valid checksum proves well-formedness but not manufacturer issuance. It stops short of stating the return shape or failure behavior, which matters given there is no 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?

Three short sentences, each earning its place: the mechanism, the practical benefit, and the critical caveat. The mechanism is front-loaded and nothing is redundant.

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?

The validity caveat is exactly the kind of context an agent needs before acting on the result, and the offline/no-network behavior is fully covered. The one gap is the return value (boolean pass/fail vs. an error), which is not described and cannot be inferred since no output schema exists.

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 the single 'vin' parameter, so the schema already documents the input. The description adds no syntax, format, or length constraints beyond what the schema states (uppercasing, whitespace stripping), so the baseline of 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 — verify a VIN against the ISO 3779 / 49 CFR §565.15 check-digit checksum — and names the exact standard applied. It is clearly distinguishable from decode_vin and buy_vin_report by being an offline validity check rather than a data lookup.

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 positions the tool as a pre-flight typo check 'before consuming a paid API call,' which effectively routes the agent away from the costlier buy_vin_report sibling. It does not name the sibling tools directly or state exclusions (e.g. when decoding is still required afterward), so it falls 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.