Skip to main content
Glama

get_nearby_events

Read-only

Find live road incidents, closures, chain advisories, and wildfires near a place or coordinates across 37 states, normalized from state DOT and highway patrol feeds.

Instructions

Live road events near a place, in any of the 37 states CommuteScout covers (get_coverage lists them and what each state publishes).

Data: the same feeds the live map shows, normalized - state DOT and highway-patrol incidents, roadwork and closures, chain and traction advisories, and nationwide wildfires. Every event names its publishing agency in the source field. What a state publishes varies (some publish roadwork only), so a quiet answer can be normal there. This is the right tool for "what's happening near X" in every state, California included; in California the California-only tools add dispatch logs, lane counts and chain levels.

center is "lat,lon"; or pass place (an address or place name) instead. kinds is a comma list from: incident, closure, chain, fire, sign, rwis, camera, toll (toll adds live and fixed toll prices where agencies publish them), enforcement (speed and red-light cameras from OpenStreetMap). radius_km caps at 160.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_nearby_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNoincident,closure,chain,fire
placeNo
centerNo
radius_kmNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.132.0
    • addedInput schema / properties / center / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / center / default
      Added value: +null
    • removedInput schema / properties / center / type
      Removed value: -"string"
    • addedInput schema / properties / place
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Place"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "center"
      -]
  2. First observedv2.82.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description's job is incremental and it delivers: it identifies the underlying feeds (state DOT, highway patrol, wildfires), notes normalization, says every event names its publishing agency in the source field, and explains that per-state publishing variability makes sparse results normal. No information about result caps, ordering, or pagination is given.

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 the core purpose followed by data provenance, routing guidance, then parameter usage; the ordering is sensible. Some material, such as the parenthetical sourcing of enforcement data and the toll pricing aside, could be trimmed without loss, and the line-broken layout is slightly noisy.

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?

With no output schema, the description does the work of indicating what an event contains (agency in source, several event categories) and how coverage varies by state. It leaves the actual response shape, field set, and result volume unstated, which matters for a multi-kind query tool returning potentially large lists.

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%, so the description must carry the parameters and it does: center as 'lat,lon' with place as an alternative, kinds as an enumerated comma list with parenthetical meanings for toll and enforcement, and the 160 km cap on radius_km. This adds substantial meaning the bare schema does not convey, including the unrecognized-by-schema 'toll' and 'enforcement' values.

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?

Names a concrete resource and scope: 'Live road events near a place' across 37 states, and explicitly separates itself from the California-only tools by saying those add dispatch logs, lane counts and chain levels. An agent can distinguish this from siblings like get_incidents or get_cameras without opening a schema.

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?

Gives a clear triggering phrase ('what's happening near X'), states it is the right tool in every state including California, and routes to get_coverage for coverage details. It also warns that a quiet result can be normal where a state publishes little, which preempts a misread of an empty answer. It stops short of saying when a narrower sibling (get_incidents, get_lane_closures) should replace it.

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