Running Cat Geo

Report on a given route

route_report

Read-only

A report on a route you already have: a GPX track, a line from another app, a route drawn by hand. The route is GeoJSON with [lon, lat] coordinates, such as {"type": "LineString", "coordinates": [[6.1432, 46.2044], [6.5, 46.0], [6.8694, 45.9237]]}, or a MultiLineString of sections in order; it is not re-routed. The answer has one key per part in include. profile: heights along the line with total climb and descent, following the road over bridges and through tunnels (thinned to about 150 points here); weather: the forecast at the time you reach each point, riding from departure at speedKmh; timezones: the zones crossed and where; airStations and rivers: stations and gauges near the line; layers: marked routes, protected areas, pistes, lifts and borders it follows or crosses, with the km where; surfaces: kilometres paved, unpaved and unknown and the stretches of each; landcover: what the ground is along it (forest, farmland, grassland, water, built-up and so on). A part that fails comes back under errors. Use plan_route to find a route between waypoints first, stops_along_route for water and food. Counts one request per part.

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": "route_report"
  }
}

Input Schema

Name	Required	Description
`lang`	No	Language for the names of trails, parks and areas in the layers part (name:xx in OpenStreetMap), such as en, de, pl; local names by default
`route`	Yes	GeoJSON LineString or MultiLineString, coordinates as [lon, lat]
`layers`	No	Which map layers the layers part looks at: route, protected_area, piste, aerialway, boundary; all but boundary by default
`include`	No	Parts: profile, weather, timezones, airStations, rivers, layers, surfaces, landcover; all but surfaces and landcover by default
`speedKmh`	No	Average moving speed in km/h, which sets when you reach each point for the weather
`departure`	No	Start time with offset, such as 2026-06-01T07:00:00+02:00, for the weather and time zone parts; now by default

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds real operational context beyond them: the profile is 'thinned to about 150 points here', failures surface under an 'errors' key, and 'Counts one request per part' discloses a per-part cost model. It stops short of any auth or rate-limit statement, but the cost and degradation behavior are unusually well disclosed.

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 definition of the input and the no-reroute constraint, then the output contract, then the part glossary. Dense but every sentence carries information; the long enumeration of eight parts would read better as a list, which costs it a point.

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?

With no output schema, the description takes on the return contract itself — 'one key per part in include' and 'A part that fails comes back under errors' — and explains the default coverage of include and layers. Nothing essential to calling it correctly is missing.

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, but the description goes further by explaining what each enum value actually yields (profile = heights with climb/descent over bridges and tunnels, weather = forecast at arrival time derived from speedKmh and departure, layers = km of features crossed). That meaning is not in the schema, which merely lists the enum strings.

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+resource (report on a route) and immediately scopes it: 'a route you already have: a GPX track, a line from another app, a route drawn by hand', explicitly noting 'it is not re-routed'. That contrast cleanly separates it from plan_route and the other report tools.

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 routing advice: 'Use plan_route to find a route between waypoints first, stops_along_route for water and food', plus the key exclusion that the given line is never re-routed. The agent knows both when to call this and which sibling to call instead.

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?