US truck engine reference: VIN lookup, part numbers, failure modes and NHTSA recalls.
Scored across 4 tools
Each tool has a clearly distinct input and purpose: part-number lookup, generic page retrieval, platform listing, and VIN decoding. There is little risk of confusing them, even though get_page is broad because it explicitly consumes URLs returned by the other tools.
All four tools use a consistent snake_case verb_noun pattern: find_part_number, get_page, list_platforms, lookup_vin. The naming is predictable and readable.
Four tools are well within the typical 3-15 range and each earns its place for a read-only automotive reference index. The set is compact without feeling arbitrarily thin.
The surface covers the core lookup workflows: part numbers, VINs, platform listings, and page retrieval for recalls, failure modes, repair costs, and blog content. Minor gaps exist around direct keyword search or listing content types without navigating through platform pages first.
Find which part a Ford, Mopar, GM or aftermarket part number is, which engine it fits and what it replaced or was replaced by. Dashes and spaces are ignored; at least 4 characters. Returns up to 25 parts.
| Name | Required | Description | Default |
|---|---|---|---|
| number | Yes | A part number or the start of one, e.g. 68026995AB |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely non-structured behavior: prefix matching ('or the start of one'), input normalization of dashes/spaces, minimum length, and a 25-result cap that tells the agent to narrow ambiguous queries. It stops short of describing error or empty-result 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 compact sentences: what it resolves, input constraints, and result cap. No filler, and the primary purpose is front-loaded before constraints.
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 the description compensates by enumerating what comes back (part identity, engine fitment, supersession chain, 25-result cap). It is nearly complete for a single-parameter read tool; only the shape/ordering of the returned records is left 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?
Schema coverage is 100% and the schema supplies an example, so baseline would be 3. The description goes further by explaining accepted format variations (dashes and spaces ignored), the 4-character floor, and that partial/prefix numbers are valid input — semantics an agent would otherwise have to guess.
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 (find) and resource (part number) plus the exact payload returned: which part it is, which engine it fits, and supersession info. The domain (Ford, Mopar, GM, aftermarket) makes it trivially distinguishable from siblings like lookup_vin and list_platforms.
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 implied by the purpose ('find which part...'), and there is useful input guidance (dashes/spaces ignored, minimum 4 characters, prefix allowed). However, no alternative is named and no when-not-to-use condition is given, even though lookup_vin is a plausibly confusable sibling for identification tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the markdown version of a Torque Index page by its path, e.g. /platforms/cummins-6_7/, /failure-modes//, /parts//, /recalls//, /repair-costs/, /blog//. Use the URLs returned by the other tools.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Site path or full https://torqueindex.com URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds the return format ('markdown version'), which matters since there is no output schema. It does not say what happens for an invalid or unknown path (error vs. empty result) or whether output is truncated for large pages.
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, front-loaded with the action and return format, followed by the routing hint. No filler, and the examples are compactly inlined rather than listed as prose.
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 conveys what comes back (markdown) and where valid paths come from. The only material gap is failure behavior for a malformed or nonexistent path.
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 baseline is 3, but the description earns above baseline by enumerating the concrete path shapes (/platforms/<x>/, /failure-modes/<id>/, /repair-costs/, etc.), which tells the agent what a valid path actually looks like beyond the schema's generic 'Site path or full URL' note.
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 ('Return the markdown version of a Torque Index page') plus the lookup key ('by its path'). The enumerated example paths make the resource scope concrete, and 'Use the URLs returned by the other tools' distinguishes it from the discovery-oriented siblings (list_platforms, lookup_vin, find_part_number).
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 the URLs returned by the other tools' gives explicit routing: this is the content-fetch follow-up after discovery. It lacks an explicit when-not clause (e.g., don't use for search or ID resolution), but the context for use is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every engine platform Torque Index covers, with its page, recalls page and part count.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds that each entry carries a page, recalls page and part count, but says nothing about ordering, pagination, or whether the list is complete or truncated.
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 with no filler. The resource is named first and the return fields follow, so an agent gets the essentials immediately.
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 usefully enumerates the notable fields returned. For a zero-parameter read-only listing tool, that is close to sufficient; only ordering/pagination behavior is left 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?
The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. It correctly signals that 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?
Names a specific verb (List) and resource (engine platforms) and states the scope Torque Index covers. Siblings (find_part_number, get_page, lookup_vin) are retrieval-by-key tools, so a catalog-listing tool is naturally distinguishable without needing an explicit contrast.
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 framing implies 'use this to discover which platforms exist,' but there is no explicit when/when-not guidance or reference to alternatives. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Decode a 17-character VIN (via NHTSA vPIC) and return the matching Torque Index engine platform, vehicle configuration pages and the recalls and bulletins that apply. Fitment is year x model x engine; cab and wheelbase are not modeled.
| Name | Required | Description | Default |
|---|---|---|---|
| vin | Yes | 17 characters, letters and digits, no I, O or Q |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that: the upstream data source (NHTSA vPIC), the specific artifacts returned, and the fitment granularity limit (year x model x engine) that tells the agent what the result can and cannot resolve.
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 dense sentences: the action and returns come first, the modeling caveat second. Every clause carries information an agent needs; there is no boilerplate or restatement of the name.
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 full schema coverage and rich annotations, the description supplies the remaining essentials: source, return contents, and the fitment limitation. No output schema exists, but the description already enumerates what comes back, so nothing material 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% and the schema already documents the 17-character, no-I/O/Q format, so the baseline is 3. The description goes slightly beyond by tying the parameter to its decode source and clarifying what the resolved vehicle dimensions mean for downstream fitment decisions.
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 ("Decode a 17-character VIN") plus the data source (NHTSA vPIC) and enumerates the concrete outputs (engine platform, configuration pages, recalls and bulletins). None of the siblings (find_part_number, get_page, list_platforms) do VIN decoding, so an agent can route unambiguously without opening the 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 description establishes a clear context for use (you have a VIN and need platform/config/recall data) and adds a scope caveat that "cab and wheelbase are not modeled." It does not explicitly name alternatives or state when to prefer find_part_number or list_platforms instead, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
find_part_numberget_pagelist_platformslookup_vinUS vehicle recalls, complaints, EPA figures, VIN decode and trouble codes, with sources.
Check a US car: decode a VIN, see recalls, crash ratings, owner complaints and fuel economy.
Vehicle safety recalls, complaints, and crash data from NHTSA
Decode VINs, search recalls, complaints, crash ratings, and investigations.
Add one secure layer between your agents and this server.
