Skip to main content
Glama

Find nearby places

find_nearby_places
Read-onlyIdempotent

Find the nearest places of a type in or around a neighbourhood / district (OpenStreetMap data). Prefer a neighbourhood/district name; precise GPS coordinates are not required (if latitude/longitude are given they are rounded to ~1 km on the server). Types: pharmacy, hospital, cafe, restaurant, lodging (hotel), atm, bank, parking, gas_station, electric_vehicle_charging_station, supermarket, shopping_mall, museum, park, playground, zoo, aquarium, movie_theater, mosque, toilets, viewpoint, bowling_alley, escape_room and more. Returns name, address, distance and map/directions links. Turkish type names also work (eczane, kafe, otopark). Note: on-duty (nöbetçi) pharmacy status is not included. TR: Yakındaki yerler.

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": {
      "type": "<type>"
    },
    "name": "find_nearby_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity, e.g. Istanbul, Izmir (helps to find the place; city alone uses the city centre). Optional.
typeYesPlace type, e.g. pharmacy, cafe, restaurant, atm, parking, museum, park (or Turkish: eczane, kafe, otopark).
limitNoMaximum number of places, 1-15 (default 10).
placeNoNeighbourhood, district or landmark name, e.g. "Kadıköy Moda", "Beşiktaş", "Taksim", "Alsancak". Preferred.
latitudeNoOptional latitude; not required (rounded to ~1 km).
radiusKmNoSearch radius in km, 0.3-20 (default 3).
longitudeNoOptional longitude; not required (rounded to ~1 km).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / city
      Added value: +{
      +  "default": null,
      +  "description": "City, e.g. Istanbul, Izmir (helps to find the place; city alone uses the city centre). Optional.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedInput schema / properties / latitude / default
      Added value: +null
    • changedInput schema / properties / latitude / description
      Previous value: -"Latitude, e.g. 41.0369"New value: +"Optional latitude; not required (rounded to ~1 km)."
    • changedInput schema / properties / latitude / type
      Previous value: -"number"New value: +[
      +  "number",
      +  "null"
      +]
    • addedInput schema / properties / longitude / default
      Added value: +null
    • changedInput schema / properties / longitude / description
      Previous value: -"Longitude, e.g. 28.9850"New value: +"Optional longitude; not required (rounded to ~1 km)."
    • changedInput schema / properties / longitude / type
      Previous value: -"number"New value: +[
      +  "number",
      +  "null"
      +]
    • addedInput schema / properties / place
      Added value: +{
      +  "default": null,
      +  "description": "Neighbourhood, district or landmark name, e.g. \"Kadıköy Moda\", \"Beşiktaş\", \"Taksim\", \"Alsancak\". Preferred.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedInput schema / required
      Previous value: -[
      -  "latitude",
      -  "longitude",
      -  "type"
      -]New value: +[
      +  "type"
      +]
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), but the description adds genuinely new behavior: the server rounds coordinates to ~1 km, results include name/address/distance/map links, Turkish type aliases are accepted, and on-duty pharmacy status is explicitly excluded. That exclusion caveat is exactly the kind of limitation an agent would not otherwise know.

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

Conciseness5/5

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

The core action and the 'prefer place name over GPS' rule come first, followed by the type vocabulary and then the return/caveat details. The long type list is functional enumeration rather than filler; nothing is redundant.

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

Completeness4/5

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

With no output schema, the description carries the burden of explaining returns and does so (name, address, distance, map/directions links). It also discloses the data source and precision limitation. It stops short of saying what happens on empty results or how ties within a radius are ordered, which would fully close the loop.

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 extends the type vocabulary well beyond the schema examples (lodging, gas_station, toilets, viewpoint, escape_room) and repeats the Turkish alias and rounding behavior in context. Those additions are useful for choosing values even though the schema already documents most fields.

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 (find), resource (places), scope (nearest, in/around a neighbourhood or district), and data source (OpenStreetMap). No sibling in the provided list does anything similar, so the tool is unambiguously distinguishable.

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

Usage Guidelines4/5

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

Explicitly tells the agent to prefer a neighbourhood/district name and that precise GPS coordinates are unnecessary, which is real routing guidance for the caller. It lacks an explicit 'when not to use this' clause, which keeps it below a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources