NHTSA Vehicle Safety

get_crash_statistics

Get fatal crash statistics from the NHTSA Fatality Analysis Reporting System (FARS).

Returns fatal motor vehicle crash data for a state, including total
fatalities, fatalities by person type (drivers, passengers, pedestrians),
and alcohol-involved crashes.

Args:
    state: Two-digit state FIPS code (e.g. '06' for California, '48' for Texas)
        or two-letter state abbreviation (e.g. 'CA', 'TX').
    year: Year for statistics (e.g. 2022). Defaults to the most recent available year.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`year`	No
`state`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.1/5.0

Behavior3/5

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

With no annotations provided, the description must carry the full burden. It adds useful context such as the default year behavior and the output categories, but it does not disclose permissions, rate limits, or potential side effects. Since the tool is a read-only statistics lookup, the risk is low, but the transparency is incomplete.

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?

The description is concise and well-structured. It opens with a clear purpose statement, then lists return contents, and finally documents parameters. Each sentence adds value with no redundant or filler text.

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?

The description covers purpose, parameters, output content, and default behavior. An output schema exists, reducing the need to detail return structure. It lacks discussion of error conditions or data limitations, but for a simple fetch tool with two parameters, it is nearly complete.

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

Parameters5/5

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

Schema description coverage is 0%, but the description fully compensates. It explains the state parameter with both FIPS and abbreviation formats and examples, and explains the year parameter's default behavior. This provides complete semantic meaning beyond the basic schema types.

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?

The description specifies the exact action ('Get fatal crash statistics') and the resource ('NHTSA Fatality Analysis Reporting System (FARS)'), and lists specific returned data (fatalities, by person type, alcohol-involved). This clearly distinguishes it from sibling tools like get_complaints or get_recalls.

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

Usage Guidelines3/5

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

The intended use is implied by the resource and output content, but there is no explicit guidance on when to use this versus alternative tools. No exclusions or alternative recommendations are given, relying on the user to infer based on the data type.

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

All NHTSA Vehicle Safety tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose with no ambiguity. complaint_trends_by_component analyzes component-level trends, decode_vin decodes VINs, get_complaints retrieves complaint details, get_crash_statistics provides fatal crash data, get_recalls fetches recall information, and local_vehicle_safety_profile combines national trends with local crash data. The boundaries between tools are well-defined, preventing misselection.

Naming Consistency4/5

The naming follows a consistent verb_noun pattern with minor deviations. Most tools use get_ or decode_ prefixes (get_complaints, get_recalls, decode_vin), but complaint_trends_by_component and local_vehicle_safety_profile deviate slightly by using descriptive phrases instead of simple verbs. However, all names are snake_case and clearly describe their functions, maintaining readability.

Tool Count5/5

With 6 tools, the count is well-scoped for the NHTSA vehicle safety domain. Each tool earns its place by covering distinct aspects: VIN decoding, complaint retrieval, recall searches, crash statistics, trend analysis, and safety profiling. This provides comprehensive coverage without being overwhelming or too sparse.

Completeness5/5

The tool surface provides complete coverage for the NHTSA vehicle safety domain. It includes data retrieval (complaints, recalls, crash stats), analysis (trends, safety profiles), and utility functions (VIN decoding). There are no obvious gaps—agents can perform typical workflows like assessing vehicle safety, investigating defects, or analyzing crash data without dead ends.

Resources

Need Help?