Running Cat Geo

Trails, parks, pistes and boundaries in a box

outdoor_layers

Read-only

Features of one map layer that meet a box of up to 16 square degrees (about 4 by 4 degrees), from OpenStreetMap: name, kind, a few key tags (ref, network, operator, osmc:symbol, distance, piste:difficulty, protect_class, admin_level, website, wikidata) and each feature's bounding box; no full geometry here. Layers and their kinds: route = marked routes, kinds hiking, bicycle, mtb, foot, running; protected_area = kinds protected_area, national_park, nature_reserve; piste = ski pistes, kinds downhill, nordic, skitour, sled, hike and other piste:type values; aerialway = lifts, kinds cable_car, gondola, chair_lift, drag_lift, t-bar, platter, rope_tow, magic_carpet and other aerialway values; boundary = administrative boundaries, kinds are admin levels such as 2 (countries), 4 (regions or states), 6 (counties or districts), 8 (municipalities), larger units first. At most limit features come back; when there were more, truncated is true and the rest are left out in no particular order, so narrow the box or pass kinds. For anything else on the map (shops, peaks, springs, huts, a tag combination) use overpass_query. Counts as 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": {
      "layer": "<layer>",
      "bbox": "<bbox>"
    },
    "name": "outdoor_layers"
  }
}

Input Schema

Name	Required	Description
`bbox`	Yes	[west, south, east, north] in degrees
`kinds`	No	Only these kinds of the layer, e.g. ["hiking"] for route, ["gondola", "cable_car"] for aerialway, ["2", "4"] for boundary; all kinds by default
`layer`	Yes	route, protected_area, piste, aerialway or boundary
`limit`	No	Most features to return, 1 to 500

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 supply readOnlyHint and openWorldHint; the description adds substantial behavior beyond them: truncation is signalled by a boolean 'truncated' flag with the remainder dropped in no particular order, boundary results come back 'larger units first', kinds default to all, and the call 'Counts as one request' (quota accounting). These are exactly the traits an agent needs before deciding box size and pagination strategy.

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?

Extremely dense but front-loaded: payload, then layer/kind catalog, then truncation guidance, then the sibling escape hatch. The single long paragraph and the inline tag list ('ref, network, operator, osmc:symbol, ...') cost some readability, but nearly every clause carries decision-relevant information.

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 compensates by specifying the returned attributes and the absence of full geometry, plus the truncated flag. Combined with the box-size cap, kind vocabularies, and quota note, nothing an agent needs to call this correctly within a 4-parameter read-only tool 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 genuinely extends the schema by mapping kind vocabularies per layer (route => hiking/bicycle/mtb/foot/running, aerialway => cable_car/gondola/chair_lift/..., boundary => admin levels 2/4/6/8) and by explaining the limit/truncated interaction rather than just restating 'Most features to return, 1 to 500'.

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?

The opening clause names the specific verb and resource ('Features of one map layer ... from OpenStreetMap') and enumerates exactly what comes back (name, kind, selected tags, per-feature bbox, no geometry). The five layer values and their kind vocabularies are spelled out, so an agent can distinguish this from overpass_query and point_report without opening the schema.

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?

It states the operating envelope (a box of up to 16 square degrees), what to do when results are truncated ('narrow the box or pass kinds'), and explicitly routes other needs elsewhere: 'For anything else on the map (shops, peaks, springs, huts, a tag combination) use overpass_query.' The when-not case is named with the alternative tool.

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?