Skip to main content
Glama

Search places near a coordinate

search_places
Read-onlyIdempotent

Search real-world places (businesses, landmarks, venues) near a latitude/longitude. Returns names, structured addresses, categories, coordinates, and distances in miles, ranked by relevance then distance. Backed by open Overture Places data. Global coverage wherever the current Overture release has indexable Places data; quality varies by location. Pass q (free text), category (an exact Overture category slug such as 'pharmacy'), or both; at least one is required. A q that names a kind of place ('pharmacy', 'coffee near me', 'boots pharmacy') also searches that category: meta.interpreted_as says how q was read, and each result's match field says whether it matched by name, address, category, or name_and_category. Use mode=name to match q literally against names only. Use list_categories to find valid category slugs instead of guessing. This is proximity search only: it cannot geocode street addresses or autocomplete partial input. Each call counts as one search from the prepaid balance. Read meta.warnings: category_alias reports a reviewed legacy category resolved to resolved_category (legacy parent aliases can narrow the old filter), unknown_category lists suggested categories, no_results_within_radius includes nearest_match identifying the closest place found within the bounded 100-mile lookup, outside results, and says which radius_mi to retry with or to search from a closer point beyond the 50-mile maximum, query_relaxed means no exact matches so a loosened q was used, category_inferred means nothing matched by name so the results are nearby places in the closest category (not the named place), pagination_limit_reached means more places match beyond the 1,000-place category-browse window so narrow the search instead of paging. If a call fails with quota_exhausted, stop and tell the user instead of retrying.

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": {
      "lat": "<lat>",
      "lon": "<lon>"
    },
    "name": "search_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoFree-text search, e.g. 'ramen', 'Blue Bottle', 'pharmacy', '서울'. Category words in q also search that category unless mode=name or category is set. Use at least 3 searchable characters, or 2 contiguous CJK characters. Required unless category is supplied.
latYesLatitude of the search center.
lonYesLongitude of the search center.
modeNoMatch q against names, addresses, or both. Default 'all' (also reads category words in q). 'name' matches names literally, without category interpretation. mode=address needs at least 4 searchable characters in q.
sortNoResult order. 'relevance' (default) ranks by match quality, then distance. 'distance' returns the same matches nearest first; category pages then page by distance.
limitNoMaximum results. 1-20 without category, 1-50 when category is supplied. Default 10.
offsetNoPagination offset for category browsing; only valid with category. offset + limit must be at most 1000 (the first 1000 ranked places). Use meta.next_offset from the previous page; it is null on the last page. Each page is one search.
categoryNoExact Overture category slug, e.g. 'pharmacy', 'coffee_shop', or a parent such as 'food_and_drink' (matches its subcategories). Find slugs with list_categories. Without q, lists places in this category by distance; with q, filters text matches to it.
radius_miNoSearch radius in miles, max 50. Default 25.
min_confidenceNoOnly return places whose Overture confidence score is at least this value, 0-1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds several things annotations cannot express: each call bills one search against a prepaid balance, global coverage quality varies by location, and the 1,000-place category-browse ceiling. The meta.warnings taxonomy (category_alias, query_relaxed, category_inferred, no_results_within_radius) tells the agent how results can be silently loosened, which is unusually valuable.

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

Conciseness3/5

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

The opening two sentences are well front-loaded, but the description degenerates into a single run-on sentence cataloguing every meta.warnings code, mixing diagnosis, retry advice, and pagination advice in one clause chain. The warnings content is worth keeping, yet it would scan far better as a short enumerated list.

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 must explain returns, and it does: fields, ranking order, miles units, meta interpretation fields, and every warning code with its remediation. For a 10-parameter paid search tool with soft-matching semantics, nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all ten parameters are already documented with enums, ranges, and defaults; the description's parameter guidance ('at least one of q or category', 'mode=name matches names literally') largely restates the schema. Marginal added meaning comes from the note that legacy parent aliases can narrow an old filter, but that describes a warning rather than a parameter contract.

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 concrete verb and resource ('Search real-world places ... near a latitude/longitude') plus the returned fields (names, addresses, categories, coordinates, distances) and the data source (Overture Places). It also explicitly carves out what it is not ('proximity search only: it cannot geocode street addresses or autocomplete'), which separates it from any geocoding sibling.

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 selection rules: pass q, category, or both; use mode=name to match literally; use list_categories to find slugs 'instead of guessing'. It also names the failure-handling path ('If a call fails with quota_exhausted, stop and tell the user instead of retrying') and the pagination alternative ('narrow the search instead of paging').

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