google-maps-mcp

Maps Compute Route

maps_compute_route

Read-onlyIdempotent

Calculate route travel time and distance for driving, walking, or cycling, with up to 8 stops and optional turn-by-turn steps or alternatives.

Instructions

Travel time and distance through the stops in order (Routes API computeRoutes shape): {travelMode, routes: [{description, distanceMeters, duration, staticDuration, localizedValues, durationWithoutTraffic, durationRange, departureTime, arrivalTime, legs: [{distanceMeters, duration, staticDuration, startLocation, endLocation, localizedValues}]}], waypoints: [{query, displayName, formattedAddress, placeId, location}], googleMapsUri, condition, note}. duration is in traffic for DRIVE (now or at departureTime/arrivalTime), otherwise typical. includeSteps fills legs[].steps [{distanceMeters, staticDuration, startLocation, navigationInstruction {maneuver, instructions}, localizedValues, notices}] and legs[].segments [{instructions, distanceMeters, staticDuration, firstStepIndex, stepCount}]; includePolyline fills routes[].polyline {encodedPolyline}.

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": {
      "origin": "<origin>",
      "destination": "<destination>"
    },
    "name": "maps_compute_route"
  }
}

Input Schema

Name	Required	Description	Default
`origin`	Yes	A place name or address ('Albertina, Vienna'), a place id (ChIJ…) or 'lat,lng'
`travelMode`	No	DRIVE (default), WALK or BICYCLE	DRIVE
`arrivalTime`	No	Local wall-clock time at the stop, e.g. 2026-10-22T08:30 (no offset)
`destination`	Yes	A place name or address ('Albertina, Vienna'), a place id (ChIJ…) or 'lat,lng'
`includeSteps`	No	Add turn-by-turn steps and segments per leg
`departureTime`	No	Local wall-clock time at the stop, e.g. 2026-10-22T08:30 (no offset)
`intermediates`	No	Stops in between, in order (max 8)
`includePolyline`	No	Add the route line (encoded polyline)
`computeAlternativeRoutes`	No	Also return alternatives (max 3)

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.1Oct 29, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: 'duration is in traffic for DRIVE (now or at departureTime/arrivalTime), otherwise typical' explains what the returned numbers mean. It says nothing about failure modes (unresolvable origin, no route found), quota/rate limits, or the interaction between departureTime and arrivalTime when both are supplied.

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

Conciseness3/5

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

The purpose is front-loaded in the first clause, which is good, but the bulk of the text is a long nested enumeration of the response shape that an output schema already defines. It reads as a dense run-on where the actionable guidance (includeSteps/includePolyline/traffic semantics) is buried mid-paragraph rather than surfaced.

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

Completeness3/5

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

An output schema exists, so the extensive return-shape recital is largely redundant, while the genuinely missing context - how this differs from plan_route/show_route, whether departureTime and arrivalTime are mutually exclusive, what happens when no route is found - is absent. The definition is complete on data shape but incomplete on decision-making.

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 baseline is 3, but the description earns more by explaining parameter effects on the response: includeSteps fills legs[].steps and legs[].segments, includePolyline fills routes[].polyline, and travelMode changes whether duration includes traffic. That is meaning the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause 'Travel time and distance through the stops in order' gives a specific verb-plus-resource, and the mention of ordered stops plus the Routes API shape makes the scope concrete. It never distinguishes itself from siblings like maps_plan_route, maps_show_route, or maps_compute_route_matrix, so an agent cannot tell from the description alone which route tool to pick.

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

Usage Guidelines2/5

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

There is no when-to-use statement, no exclusion, and no mention of any sibling alternative. Given that the sibling set contains three other route-related tools (plan_route, show_route, compute_route_matrix), this omission is a real gap rather than a minor one.

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

Deploy Server