Running Cat Geo

Plan a route

plan_route

Read-only

Finds a route on OpenStreetMap roads and paths through 2 to 50 waypoints, in the order given, and optionally reports on it. Returns length (km), climb (m), duration, kilometres paved, unpaved and unknown, kilometres per road type, and an outline of about 40 [lon, lat] points (not the full line). With report it adds, for the route found: the elevation profile, the weather at the time you reach each point, time zones, air quality stations, river gauges, map layers, surfaces or land cover. Use plan_loop instead for a round trip of a given length from one start, and route_report for a line you already have (a GPX track, a route from another app). If a waypoint cannot be reached with the profile (a pedestrian zone for a car, a footpath for a road bike) the answer is an error saying no route; move the point or change the profile. A route counts once per started 100 km (50 km for mtb); each report part counts one request.

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": {
      "points": "<points>"
    },
    "name": "plan_route"
  }
}

Input Schema

Name	Required	Description	Default
`points`	Yes	Waypoints as [lon, lat], start first, finish last, e.g. [[6.1432, 46.2044], [6.8694, 45.9237]]
`report`	No	Report parts about the route found; none by default
`profile`	No	bike: touring bike on quiet roads and good tracks; city: a bike that keeps to cycleways and off busy roads; road-bike: fast on asphalt; quiet-road-bike: asphalt with as little traffic as possible; gravel: unpaved tracks welcome; mtb: trails; hiking: footpaths, mountain paths included; car; shortest: the shortest line on any way	bike
`speedKmh`	No	Average speed for the weather timing, default 20
`departure`	No	ISO time with offset, for the weather; now by default
`alternative`	No	0: the best route for the profile; 1 to 3: the first, second or third alternative, each a different way between the same waypoints (ask for them one at a time to compare)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behaviour beyond them — the return shape and its approximation ("an outline of about 40 [lon, lat] points (not the full line)"), what each report part contributes, the error semantics when a waypoint is unreachable for the profile, and the billing granularity (once per started 100 km, each report part one request). None of this is recoverable from the annotations or schema.

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 verb and return values, then alternatives, then error behaviour, then cost. Every sentence carries information, with no filler. It is a dense block rather than scannable bullets, which costs it slightly, but nothing is redundant.

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?

There is no output schema, so the description must define the return values — and it does in detail (length, climb, duration, surface splits, outline point count). Combined with coverage of failure modes, alternatives, and request cost, an agent has everything needed to call this correctly and interpret the response.

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% and the enum descriptions are already thorough, so the schema carries most parameter meaning. The description still adds meaning the schema does not: waypoints are traversed "in the order given", report parts are computed "for the route found", and route after the error note hints that the profile governs reachability. It does not restate the individual enum values, which is correct given 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?

States a specific verb and resource ("Finds a route on OpenStreetMap roads and paths") plus the scope constraint (2–50 waypoints, in the given order). It explicitly names plan_loop and route_report as the tools for different shapes of request, so an agent can distinguish it from siblings without reading their schemas.

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 explicit alternatives with conditions: plan_loop "for a round trip of a given length from one start", route_report "for a line you already have (a GPX track, a route from another app)". It also explains the failure mode ("the answer is an error saying no route; move the point or change the profile") and the cost model, which shapes how an agent should batch calls.

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

All Running Cat Geo 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?