Skip to main content
Glama

Road conditions now: closures, chains, weather

dogpolicies_road_conditions
Read-onlyIdempotent

Do I need chains on I-80 to Tahoe right now? Is US-50 open over Echo Summit? Caltrans chain controls, lane and ramp closures, road-weather stations and message-sign text on I-80 (San Francisco to the Nevada line), US-50 (West Sacramento to Stateline), I-15 (San Diego to Primm) and I-5 in California, each at its route mile with the nearest dog stop. Live state, not rules: Caltrans feed data fetched every 15 minutes (fetched_at in the result), never a verified fact. For the day of a mountain or desert drive: Donner Summit, Echo Summit, Cajon Pass, the Grapevine. It reports conditions, not places to stop: each condition carries only the nearest dog stop. Nevada roads and other highways are not covered. Inputs: route ("I-80", "80", "US 50", "Highway 50", "I-15", "I-5"); a window as from_mile and to_mile, or town (a town or named stretch on the route: Truckee, Donner Pass, South Lake Tahoe, Placerville, Cajon Pass, Barstow) with direction and ahead_miles; direction alone keeps that direction's closures, signs and chain controls. With no window, the whole route in California. chain_controls_in_effect is true when a Caltrans chain-control point in the window reports a control (any status but R-0), with Caltrans' own wording; a sign that mentions chains is listed under signs with its text. Each weather station says whether its reading is current (the feeds sometimes carry readings months old; those numbers are left out of the text). A document older than two hours is marked stale; when no document can be read the answer has outcome unavailable and the address of Caltrans QuickMap, the live map.

Examples:

  • "Do I need chains on I-80 to Tahoe right now?" -> route="I-80", direction="east"

  • "Is Highway 50 open over Echo Summit?" -> route="Highway 50", town="Echo Summit"

  • "Closures on I-15 from Barstow to the Nevada line" -> route="I-15", town="Barstow", direction="north", ahead_miles=120

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "route": "<route>"
    },
    "name": "dogpolicies_road_conditions"
  }
}

Input Schema

NameRequiredDescriptionDefault
townNoA town or named stretch on the route ("Truckee", "Donner Pass", "South Lake Tahoe", "Cajon Pass", "Barstow")
routeYesThe highway in California: "I-80", "80", "US 50", "Highway 50", "I-15" or "I-5"
to_mileNoEnd of a mile range on the route
directionNoDirection of travel. Keeps that direction's closures, signs and chain controls (and those for both ways); with town, the window runs ahead of it. North and east mean increasing route miles
from_mileNoStart of a mile range on the route (the road-trip guide's miles)
ahead_milesNoWith town: miles from it in the direction of travel (default 50), or on each side of it without a direction (default 25)
response_formatNo'markdown' for readable text, 'json' for structured datamarkdown

Output Schema

NameRequiredDescriptionDefault
codeNoWith an outcome other than ok: not_found, invalid, unavailable
nextNoCalls that would answer the question, in words
roadYesThe road as signed, e.g. "I-80"
as_ofYesDate the data was built (YYYY-MM-DD)
routeYesRoute id (i-80, us-50, i-15, i-5); null when the route is not covered
signsYes
staleNoTrue when the document is older than two hours
countsYes
noticeYes
sourceYes
windowYes
licenseYes
messageNoWhat happened, in a sentence
nearestNoWhen nothing is inside the radius: the nearest places in the data, with distance_miles
outcomeNoAbsent or ok: a normal answer. no_match: nothing in the data matches, see did_you_mean, nearest and next. bad_input: the arguments cannot be used as given, see next. partial: some of the ids were found, see missing. unavailable: a live source could not be read. None of these is an error.
weatherYesRoad-weather stations in the window; current is false when the station's reading is more than two hours older than fetched_at
acceptedNoWith bad_input: each argument that could not be read, with the values it accepts
closuresYes
live_mapYesCaltrans QuickMap, the live map of the same feeds
fetched_atYesWhen the loop fetched the feeds; null when no document could be read
did_you_meanNoClose matches to what was asked for: towns, places, slugs or brands, best first
feeds_failedYesDistrict feeds that did not answer at the last fetch
resolved_fromNoSet when a word was read as the value the tool uses: hotel as lodging, NB as north. Each key is the argument; asked is what was sent, used what it was read as
chain_controlsYesThe chain-control points in the window with a control in effect
attribution_urlYes
attribution_textYes
chains_in_effectYesA chain control in effect or a sign that mentions chains, counted the same way as in the I-5 conditions answer
chain_controls_in_effectYesA Caltrans chain-control point in the window reports a control in effect

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds substantial behavior the annotations cannot express: 15-minute feed freshness with fetched_at, 'never a verified fact', two-hour staleness marking, omission of months-old weather readings, and the unavailable outcome plus QuickMap fallback address.

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 user questions it answers, then scope, freshness caveats, inputs, and examples — a sensible order with little filler. It is long, and the opening question 'Do I need chains on I-80 to Tahoe right now?' is repeated verbatim in the Examples block, a small redundancy.

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 7-parameter tool with an output schema present, the description covers everything an agent needs: freshness and reliability caveats, the meaning of chain_controls_in_effect, stale and unavailable outcomes, and geographic exclusions. Return-value structure is correctly left to the output schema.

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; the description earns above that by explaining how the two windowing modes interact (from_mile/to_mile versus town plus direction and ahead_miles), that direction alone keeps that direction's closures/signs/chain controls, and that no window means the whole route in California. It largely restates the route and town examples already present in the schema.

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 specific verb/resource pair (Caltrans chain controls, closures, road-weather stations, sign text) and scopes it to four named California routes with mile markers. It also draws an explicit boundary — 'reports conditions, not places to stop' — which separates it from place/stop-oriented siblings without needing to name them.

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?

Strong usage context: 'for the day of a mountain or desert drive' with named passes, plus a clear when-not boundary ('Nevada roads and other highways are not covered') and three worked query-to-parameter examples. It does not name any sibling tool as the alternative for out-of-scope requests, which keeps it 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.