Skip to main content
Glama

plan_trip

Read-only

Get the full picture of a US drive in one call: route options, traffic-aware drive time for your departure, live incidents, closures, weather alerts and forecast, plus a summary to lead with.

Instructions

Everything about one drive between any two US places, in one call.

Use this for "how's the drive to X", "how long to get to Y at 5", "anything on the way to Z". It returns:

  • the route (miles, main roads, alternatives) from the closure-aware planner the CommuteScout map uses: fully closed roads are avoided and routes are ranked by what is on them;

  • drive time for that departure: with traffic, typical for that weekday and hour, and with no traffic (TomTom historical speed profiles; live traffic too when leaving within the hour);

  • every live event ON the route, ordered by mile: incidents, closures, chain controls, message signs, cameras (with image URLs), road-weather stations, tolls, speed and red-light cameras, and wildfires near it;

  • NWS weather alerts along the route and the forecast at the destination for the arrival hour;

  • a one-paragraph summary to lead the answer with, and notes for anything missing or degraded.

Lead with summary, then the items that change the user's plan. For WHEN to leave, call best_time_to_go instead. If the answer has needs_clarification, ask the user which option they meant.

Input Schema

NameRequiredDescriptionDefault
originNoAn address, landmark or place anywhere in the US, e.g. '1600 Pennsylvania Ave, Washington DC' or 'Pike Place Market'. Include city and state when you have them. 'home', 'work' or a saved place's name use the user's saved places (see get_my_places). Leave origin out to start from the user's Home.
depart_atNoWhen the user leaves, in the origin's local time: 'now' (default), 'tomorrow 8am', '17:30', 'friday 7:15am' or ISO '2026-11-02T08:00'.
preferenceNoRoute preference.fastest
destinationNoAn address, landmark or place anywhere in the US, e.g. '1600 Pennsylvania Ave, Washington DC' or 'Pike Place Market'. Include city and state when you have them. 'home', 'work' or a saved place's name use the user's saved places (see get_my_places). Leave origin out to start from the user's Home.
origin_coordsNoExact 'lat,lon' instead of a place name, e.g. '47.6097,-122.3421'. Wins over the place name.
destination_coordsNoExact 'lat,lon' instead of a place name, e.g. '47.6097,-122.3421'. Wins over the place name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.132.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover readOnly/openWorld; the description goes much further, disclosing the closure-aware planner and route ranking, that live traffic is used only when leaving within the hour (historical profiles otherwise), that degraded/missing data surfaces in `notes`, and that a clarifying-question path exists. This is exactly the extra context annotations cannot carry.

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 purpose sentence, then a scannable bullet list of outputs, then response-handling guidance — well ordered. It is long, and a couple of phrases (TomTom historical speed profiles, image URLs) are decorative rather than decision-relevant, keeping it just below top marks.

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?

No output schema exists, yet the description enumerates the return contents including the `summary` and `notes` fields and the needs_clarification branch, and states how to order the answer. For a complex, zero-required-parameter tool, nothing an agent needs to call or interpret it is missing.

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

Parameters3/5

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

Schema coverage is 100% and each parameter already documents formats, defaults and precedence (coords win over place names, omission defaults to Home). The description adds little parameter-level insight and notably leaves `preference` enum values (avoid_chains, no_tolls) unexplained beyond the schema's terse 'Route preference.' Baseline 3 is appropriate.

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?

Opens with a specific verb+resource+scope: 'Everything about one drive between any two US places, in one call.' The enumeration of returned artifacts (route, drive times, on-route events, weather alerts, summary) makes the capability unambiguous and clearly broader than single-purpose siblings like get_traffic or get_cameras.

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?

Gives concrete trigger phrasings ('how's the drive to X', 'how long to get to Y at 5', 'anything on the way to Z') plus an explicit exclusion routing to best_time_to_go for departure-time questions. It also tells the agent how to handle the needs_clarification response, closing the loop on ambiguity.

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