Running Cat Geo

Overpass QL query

overpass_query

Read-only

For any OpenStreetMap question the other tools do not cover: shops of one brand, peaks over 3000 m, springs, huts, benches with a view, any tag combination. Runs an Overpass QL query on OpenStreetMap data and returns Overpass JSON. Supports tag filters, bbox, around (a point or a line), poly, area (administrative boundaries and protected areas), is_in, unions and out body/tags/center/geom/count. Every query needs a bbox, around, poly, area or id; no recursion (> <). With openAt, only places whose opening_hours say they are open at that local time come back, and open_at in the answer counts how many were open, closed or had no readable hours. Answers are capped in size by plan; keep boxes small and use out center or out tags when the geometry is not needed. Use stops_along_route for stops along a route, outdoor_layers for marked trails, parks and pistes, point_report for what is at one place. 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": {
      "query": "<query>"
    },
    "name": "overpass_query"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	The Overpass QL script, with [out:json], such as [out:json];node[amenity=drinking_water](46.1,6.0,46.3,6.3);out;
`openAt`	No	Local time at the places, YYYY-MM-DDTHH:MM, e.g. 06:59 on a weekday to find places that open before 7

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 readOnly and openWorld; the description adds substantial behavior: the required spatial constraint (bbox, around, poly, area or id), the prohibition on recursion, the openAt filtering semantics plus what open_at reports in the answer, plan-based result capping, and the 'counts as one request' cost signal. Cost capping and the advise-to-shrink-bbox guidance are exactly the operational traits an agent needs and cannot get from annotations.

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 purpose and the fallback rationale, then constraints, then sibling routing — a sensible order. Some sentences are run-on (the 'Supports tag filters, bbox, around..., unions and out body/tags/center/geom/count' list and the openAt sentence pack several ideas together), but nothing is redundant filler.

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, so the return format is named (Overpass JSON) and the open_at summary field is explained. Given a two-parameter tool that executes arbitrary user-supplied QL, the description covers the mandatory spatial clause, syntax restrictions, result-size limits, and avoidance strategies — everything needed to call it without failure.

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 goes further by enumerating what the query string may contain (tag filters, around on a point or line, is_in, unions, out body/tags/center/geom/count) and the hard validation rule that every query needs a bbox/around/poly/area/id. For openAt it adds that open_at in the response counts open/closed/no-readable-hours, which the schema does not say.

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 — 'runs an Overpass QL query on OpenStreetMap data and returns Overpass JSON' — and immediately delimits scope: 'For any OpenStreetMap question the other tools do not cover'. The example uses (shops of one brand, peaks over 3000 m, springs, benches with a view) make the domain concrete enough to distinguish it from point_report or outdoor_layers.

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 both positive routing ('any OSM question the other tools do not cover') and explicit negative routing to three named siblings: stops_along_route for route stops, outdoor_layers for marked trails/parks/pistes, point_report for a single place. It also states the escape hatch — fall back to this tool when the specialized ones don't fit.

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?