Skip to main content
Glama
lzinga

US Government Open Data MCP

by lzinga
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

nhtsa_models

Read-onlyIdempotent

Find vehicle models by make and year affected by recalls or complaints, or retrieve the full model list from vPIC.

Instructions

List vehicle models for a make and year that have recalls or complaints. Or list all models for a make from the vPIC database (omit issue_type).

Example: make='tesla', model_year=2024, issue_type='r'

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
makeYesVehicle make: 'toyota', 'ford', 'tesla'
issue_typeNo'r' for recalls, 'c' for complaints. Omit for general model list.
model_yearNoModel year (optional for vPIC lookup)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv2026.4.11
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / issue_type
      Added value: +{
+  "description": "'r' for recalls, 'c' for complaints. Omit for general model list.",
+  "enum": [
+    "r",
+    "c"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / make / description
      Previous value: -"Vehicle make (e.g. 'honda', 'toyota', 'ford')"New value: +"Vehicle make: 'toyota', 'ford', 'tesla'"
    • changedInput schema / properties / model_year / description
      Previous value: -"Optional model year filter"New value: +"Model year (optional for vPIC lookup)"
    • addedInput schema / properties / model_year / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / model_year / minimum
      Added value: +-9007199254740991
    • changedInput schema / properties / model_year / type
      Previous value: -"number"New value: +"integer"
  2. First observedv2026.3.9

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds the distinction between filtered and unfiltered lists, but does not disclose return format, pagination, or any other behavioral caveats. With annotations covering safety, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences plus a helpful example. The purpose is front-loaded, and every word adds information. No fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (list of models), the description covers the inputs and the two modes. It does not describe the output format (e.g., list of model strings), but since there is no output schema and the tool is straightforward, this is a minor gap. Annotations handle safety, so overall it is complete enough for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for all three parameters, so baseline is 3. The description adds value by explaining the meaning of issue_type ('r' for recalls, 'c' for complaints), clarifying that omitting it yields the general list, and providing a concrete example that ties parameters together. This goes beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States the specific action (list vehicle models) with clear distinction between two modes (filtered by issue_type or all models). The example makes it concrete. It is clearly differentiated from sibling tools like nhtsa_makes (makes) and nhtsa_model_years (years) by focusing on models.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides an example and explains when to omit issue_type to get the general vPIC list. It doesn't explicitly state when to avoid this tool or name alternatives, but the purpose is clear enough. It could mention that for recall details one would use nhtsa_recalls, but that's implied.

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

Deploy Server

Other Tools