Bridges — FHWA National Bridge Inventory: Condition, Posting & Clearance

search_bridges

Read-onlyIdempotent

Search US bridges in the FHWA National Bridge Inventory. Scope with state, county (3-digit FIPS code), and/or condition (Good/Fair/Poor); optional filters: posting_status (open/posted/closed/not_yet_open), owner_code, scour_critical, year_min/year_max, min_adt, route, and q (text match on facility carried, feature crossed, location). Returns decoded records with condition rollup, posting status, clearances, and labels. Read-only lookup of the FHWA NBI 2025 annual snapshot; no API key. limit defaults to 100 (max 1000); offset defaults to 0, pass offset in multiples of limit to page. Use find_bridges_nearby instead for radius queries around a point, get_worst_bridges instead for Poor-condition lists, and list_bridges_in_county instead for all bridges in one county.

Input Schema

Name	Required	Description
`q`	No	Text match: facility carried / feature crossed / location
`limit`	No	Max results, default 100, at most 1000
`route`	No	Route number carried, e.g. '90'
`state`	No	US state postal code, e.g. 'IL'
`county`	No	3-digit FIPS county code within the state
`offset`	No	Results to skip for paging, default 0
`min_adt`	No	Minimum average daily traffic
`year_max`	No	Latest year built
`year_min`	No	Earliest year built
`condition`	No	Condition rating: Good, Fair, or Poor
`owner_code`	No	Agency code of the bridge owner
`posting_status`	No	Posting status: open, posted, closed, or not_yet_open
`scour_critical`	No	Only scour-critical bridges, when true

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 31, 2026
- addedInput schema / properties / condition / description
```
Added value: +"Condition rating: Good, Fair, or Poor"
```
- addedInput schema / properties / limit / description
```
Added value: +"Max results, default 100, at most 1000"
```
- addedInput schema / properties / offset / description
```
Added value: +"Results to skip for paging, default 0"
```
- addedInput schema / properties / posting_status / description
```
Added value: +"Posting status: open, posted, closed, or not_yet_open"
```
- addedInput schema / properties / scour_critical / description
```
Added value: +"Only scour-critical bridges, when true"
```
- addedInput schema / properties / year_max / description
```
Added value: +"Latest year built"
```
- addedInput schema / properties / year_min / description
```
Added value: +"Earliest year built"
```

Changed1 schema field changedOct 28, 2026

addedInput schema / properties / owner_code

Added value: +{
+  "description": "Agency code of the bridge owner",
+  "type": "string"
+}

First observedOct 25, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description is free to add what they can't: FHWA NBI 2025 annual snapshot, no API key required, limit default 100 max 1000, and offset paging in multiples of limit. It also previews the return shape ('decoded records with condition rollup, posting status, clearances, and labels'). Only gap is no statement about what happens when no filters are supplied (full-dataset scans).

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

Conciseness4/5

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

Front-loaded with purpose, then scope, then filters, then return/paging, then alternatives — a sensible ordering. The filter enumeration partially duplicates the schema's property names, costing a little density, but nothing is filler.

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

Completeness5/5

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

For a 13-parameter read-only search with no output schema, the description covers dataset vintage, auth requirements, default and maximum page size, paging semantics, return payload contents, and sibling disambiguation. An agent has everything needed to call it correctly on the first attempt.

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%, so the baseline is 3, but the description adds real value beyond the schema: it groups parameters into scoping fields (state, county FIPS, condition) versus optional filters, and it clarifies the paging contract ('pass offset in multiples of limit to page') which the schema's 'results to skip' does not convey.

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 a specific verb and resource ('Search US bridges in the FHWA National Bridge Inventory') and immediately frames the dataset provenance. The scope sentence (state/county/condition) lets an agent distinguish this general search from the specialized siblings 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.

Usage Guidelines5/5

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

Explicitly routes to three alternatives with the condition that selects each: find_bridges_nearby for radius queries, get_worst_bridges for Poor lists, list_bridges_in_county for single-county enumeration. This is the when-to-use/when-not pattern at its clearest.

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

All Bridges — FHWA National Bridge Inventory: Condition, Posting & Clearance tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?