Skip to main content
Glama

openstreetmap-mcp-server

Find OSM features near a point

openstreetmap_query_nearby
Read-onlyIdempotent

Find OSM features within a radius of a point via the Overpass API, the tool for "what is near X?" questions. Filter with amenity, or with tag_key plus an optional tag_value, ANDing up to five more filters; every feature returns with its full OSM tag set (no extratags flag here), sorted nearest-first by distance_meters, with nodes covering standalone POIs and ways covering buildings and areas.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latYesCenter latitude in WGS84 decimal degrees.
lonYesCenter longitude in WGS84 decimal degrees.
limitNoMaximum results to return. Applied after the Overpass query — if the area has more features, they are truncated.
offsetNoNumber of matching features to skip before applying limit, for paging through a large result set. Features are distance-sorted before paging, so higher offsets return progressively farther matches; the full set is cached ~10 minutes so re-paging costs no extra upstream request. Pass the nextOffset value from a prior truncated response.
amenityNoOSM amenity tag value (e.g. "hospital", "pharmacy", "restaurant", "atm"), shortcut for tag_key="amenity". Exactly one primary mode is required: this or tag_key, never both.
filtersNoUp to five additional filters, ANDed with the required primary amenity or tag_key filter in input order. Omitted or [] adds no conditions. Keys must be unique after trimming; keys and values must not contain Overpass QL metacharacters (" \ [ ] ; ( )).
tag_keyNoPrimary OSM tag key (e.g. "leisure", "shop", "highway"); omit tag_value to match any feature carrying the key, or supply it for exact equality. The alternative to amenity, never both. Additional filters are ANDed with this tag.
tag_valueNoLiteral value paired with tag_key for exact equality (e.g., "park", "supermarket"); omit for key existence. Explicit empty or whitespace-only values are invalid. Keys and values are trimmed; blank unused fields are ignored in amenity mode.
element_typesNoOSM element types to search, at least one. Ways cover most buildings and areas; nodes cover most standalone POIs. Add "relation" for complex structures like large campuses. Omit the field to search nodes and ways; an empty array is rejected because it can only match nothing.
radius_metersNoSearch radius in meters. Max 50,000m (50km). Keep under 5,000m for dense urban POI queries to avoid slow responses.
timeout_secondsNoOverpass query timeout in seconds. Increase for large radius or dense areas.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
noticeNoWhy this page is empty and what to try: nothing matched (widen the radius or change the tag), or offset ran past the end (retry lower). Absent when results were returned.
elementsNoMatching OSM features, up to the limit.
truncatedNoTrue if results were cut at the limit. Reduce radius, add more specific tags, or page with offset to retrieve the rest.
nextOffsetNoOffset to pass on the next call to retrieve the following page of features. Present only when more features remain beyond this page.
totalFoundNoTotal features returned by Overpass before limit truncation.
attributionNoRequired data attribution: Data © OpenStreetMap contributors, ODbL 1.0.
effectiveTagNoThe full ordered AND filter chain: key=value for equality, key alone for existence (e.g. "amenity=restaurant, cuisine=italian, name").
data_timestampNoOSM data freshness timestamp from the Overpass response. Absent when the endpoint reported no freshness metadata.
servingEndpointNoOverpass endpoint that answered, as origin and path. May name a failover mirror, or the endpoint that originally served a cached response. Read with data_timestamp when a result looks slow, sparse, or stale.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Tag modes conflict or are missing, a key or supplied value is blank, keys repeat after trimming, or a filter carries Overpass QL metacharacters. `query_timeout`: The query exceeded timeout_seconds. `result_too_large`: Overpass ran out of memory on this query. `rate_limited`: Every configured endpoint refused the query as throttled — HTTP 429, or a throttle document in place of JSON. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion. `overpass_gateway_timeout`: Overpass answered HTTP 504 — the query exceeded the endpoint's own time budget, not timeout_seconds. `overpass_unavailable`: Overpass answered an HTTP 5xx other than 504 — the endpoint is down, restarting, or shedding load. `endpoints_exhausted`: No endpoint answered within its attempt window, or the total time budget ran out first. `endpoints_unavailable`: No configured endpoint would serve the call — connections refused, DNS failures, throttling, or instance faults, in some mix. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Tag modes conflict or are missing, a key or supplied value is blank, keys repeat after trimming, or a filter carries Overpass QL metacharacters. `query_timeout`: The query exceeded timeout_seconds. `result_too_large`: Overpass ran out of memory on this query. `rate_limited`: Every configured endpoint refused the query as throttled — HTTP 429, or a throttle document in place of JSON. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion. `overpass_gateway_timeout`: Overpass answered HTTP 504 — the query exceeded the endpoint's own time budget, not timeout_seconds. `overpass_unavailable`: Overpass answered an HTTP 5xx other than 504 — the endpoint is down, restarting, or shedding load. `endpoints_exhausted`: No endpoint answered within its attempt window, or the total time budget ran out first. `endpoints_unavailable`: No configured endpoint would serve the call — connections refused, DNS failures, HTTP refusals such as 401/403/404, throttling, or instance faults, in some mix. Other values are possible when a failure originates below the handler."
  2. Changed5 schema fields changed
    • changedInput schema / properties / amenity / description
      Previous value: -"OSM amenity tag value (e.g., \"hospital\", \"pharmacy\", \"restaurant\", \"school\", \"atm\"). Shortcut for tag_key=\"amenity\". Cannot be combined with tag_key/tag_value."New value: +"OSM amenity tag value (e.g. \"hospital\", \"pharmacy\", \"restaurant\", \"atm\"), shortcut for tag_key=\"amenity\". Exactly one primary mode is required: this or tag_key, never both."
    • changedInput schema / properties / tag_key / description
      Previous value: -"Primary OSM tag key (e.g., \"leisure\", \"shop\", \"highway\", \"natural\"); omit tag_value for key existence, or supply it for exact equality. Cannot be combined with amenity. Additional filters are ANDed with this tag."New value: +"Primary OSM tag key (e.g. \"leisure\", \"shop\", \"highway\"); omit tag_value to match any feature carrying the key, or supply it for exact equality. The alternative to amenity, never both. Additional filters are ANDed with this tag."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Primary tag modes conflict or are missing, a tag key or supplied value is blank, keys repeat after trimming, or any filter contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. Every one of them surfaces as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered — each accepted the query and held the connection past its attempt window instead of failing outright, or the call ran out of its total time budget before another endpoint could be tried. The message names each endpoint and the window it was given. `endpoints_unavailable`: No configured Overpass endpoint could serve the call — the hosts refused the connection, could not be resolved, were throttled, or reported their own instance fault, in some mix. The message names each endpoint and what it did. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Tag modes conflict or are missing, a key or supplied value is blank, keys repeat after trimming, or a filter carries Overpass QL metacharacters. `query_timeout`: The query exceeded timeout_seconds. `result_too_large`: Overpass ran out of memory on this query. `rate_limited`: Every configured endpoint refused the query as throttled — HTTP 429, or a throttle document in place of JSON. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion. `overpass_gateway_timeout`: Overpass answered HTTP 504 — the query exceeded the endpoint's own time budget, not timeout_seconds. `overpass_unavailable`: Overpass answered an HTTP 5xx other than 504 — the endpoint is down, restarting, or shedding load. `endpoints_exhausted`: No endpoint answered within its attempt window, or the total time budget ran out first. `endpoints_unavailable`: No configured endpoint would serve the call — connections refused, DNS failures, throttling, or instance faults, in some mix. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when the page came back empty. Distinguishes a query that matched nothing (try a larger radius or different tag) from an offset past the end of a non-empty result set (retry at a lower offset). Absent when results were returned."New value: +"Why this page is empty and what to try: nothing matched (widen the radius or change the tag), or offset ran past the end (retry lower). Absent when results were returned."
    • changedOutput schema / properties / servingEndpoint / description
      Previous value: -"Overpass endpoint that produced this response, as origin and path. Differs from the first configured endpoint when a mirror answered after the primary failed, and names the endpoint that served a cached response rather than the one this call would have tried. Pair it with data_timestamp when a result looks unexpectedly slow, sparse, or stale."New value: +"Overpass endpoint that answered, as origin and path. May name a failover mirror, or the endpoint that originally served a cached response. Read with data_timestamp when a result looks slow, sparse, or stale."
  3. Changed2 schema fields changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Primary tag modes conflict or are missing, a tag key or supplied value is blank, keys repeat after trimming, or any filter contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. Every one of them surfaces as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered when the call ran out of its total time budget — each accepted the query and held the connection instead of failing outright. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Primary tag modes conflict or are missing, a tag key or supplied value is blank, keys repeat after trimming, or any filter contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. Every one of them surfaces as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered — each accepted the query and held the connection past its attempt window instead of failing outright, or the call ran out of its total time budget before another endpoint could be tried. The message names each endpoint and the window it was given. `endpoints_unavailable`: No configured Overpass endpoint could serve the call — the hosts refused the connection, could not be resolved, were throttled, or reported their own instance fault, in some mix. The message names each endpoint and what it did. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "invalid_tag",
      -  "query_timeout",
      -  "result_too_large",
      -  "rate_limited",
      -  "upstream_error",
      -  "overpass_gateway_timeout",
      -  "overpass_unavailable",
      -  "endpoints_exhausted"
      -]New value: +[
      +  "invalid_tag",
      +  "query_timeout",
      +  "result_too_large",
      +  "rate_limited",
      +  "upstream_error",
      +  "overpass_gateway_timeout",
      +  "overpass_unavailable",
      +  "endpoints_exhausted",
      +  "endpoints_unavailable"
      +]
  4. Changed6 schema fields changed
    • changedInput schema / anyOf
      Previous value: -[
      -  {
      -    "required": [
      -      "amenity"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "required": [
      -      "tag_key",
      -      "tag_value"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "required": [
      +      "amenity"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "required": [
      +      "tag_key"
      +    ],
      +    "type": "object"
      +  }
      +]
    • addedInput schema / properties / filters
      Added value: +{
      +  "description": "Up to five additional filters, ANDed with the required primary amenity or tag_key filter in input order. Omitted or [] adds no conditions. Keys must be unique after trimming; keys and values must not contain Overpass QL metacharacters (\" \\ [ ] ; ( )).",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One additional literal equality or key-existence filter.",
      +    "properties": {
      +      "key": {
      +        "description": "Literal OSM tag key. Trimmed and nonblank; must be unique across the primary tag and all filters.",
      +        "type": "string"
      +      },
      +      "value": {
      +        "description": "Literal exact-match value. Omit for key existence; an explicitly blank value is invalid. Trimmed before matching.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "key"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 5,
      +  "type": "array"
      +}
    • changedInput schema / properties / tag_key / description
      Previous value: -"OSM tag key for non-amenity queries (e.g., \"leisure\", \"shop\", \"highway\", \"natural\"). Use with tag_value. Cannot be combined with amenity."New value: +"Primary OSM tag key (e.g., \"leisure\", \"shop\", \"highway\", \"natural\"); omit tag_value for key existence, or supply it for exact equality. Cannot be combined with amenity. Additional filters are ANDed with this tag."
    • changedInput schema / properties / tag_value / description
      Previous value: -"OSM tag value paired with tag_key (e.g., \"park\", \"supermarket\", \"primary\", \"peak\")."New value: +"Literal value paired with tag_key for exact equality (e.g., \"park\", \"supermarket\"); omit for key existence. Explicit empty or whitespace-only values are invalid. Keys and values are trimmed; blank unused fields are ignored in amenity mode."
    • changedOutput schema / properties / effectiveTag / description
      Previous value: -"The OSM tag filter applied (key=value, e.g. \"amenity=cafe\" or \"leisure=park\")."New value: +"The full ordered AND filter chain: key=value for equality, key alone for existence (e.g. \"amenity=restaurant, cuisine=italian, name\")."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Both amenity and tag_key/tag_value are provided, neither is provided, or a tag key/value contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. Every one of them surfaces as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered when the call ran out of its total time budget — each accepted the query and held the connection instead of failing outright. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Primary tag modes conflict or are missing, a tag key or supplied value is blank, keys repeat after trimming, or any filter contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. Every one of them surfaces as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered when the call ran out of its total time budget — each accepted the query and held the connection instead of failing outright. Other values are possible when a failure originates below the handler."
  5. Changed1 schema field changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Both amenity and tag_key/tag_value are provided, neither is provided, or a tag key/value contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. The thrown code tracks the status: 500 and 501 surface as InternalError, every other 5xx as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered when the call ran out of its total time budget — each accepted the query and held the connection instead of failing outright. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_tag`: Both amenity and tag_key/tag_value are provided, neither is provided, or a tag key/value contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. Every one of them surfaces as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered when the call ran out of its total time budget — each accepted the query and held the connection instead of failing outright. Other values are possible when a failure originates below the handler."
  6. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "elements",
      +      "attribution",
      +      "effectiveTag",
      +      "totalFound",
      +      "truncated"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode. Declared by this tool: `invalid_tag`: Both amenity and tag_key/tag_value are provided, neither is provided, or a tag key/value contains Overpass QL metacharacters. `query_timeout`: The Overpass query exceeded the timeout. `result_too_large`: Overpass ran out of memory — the result set exceeds the server memory limit. `rate_limited`: Overpass refused the query as throttled — HTTP 429, or a throttle document instead of JSON — on every configured endpoint. With a list in OSM_OVERPASS_ENDPOINTS the call advances to the next entry first, so this surfaces only once all of them have refused it. `upstream_error`: Overpass reported a runtime error that is neither a timeout nor memory exhaustion — the message carries the remark verbatim. `overpass_gateway_timeout`: Overpass answered HTTP 504 — it accepted the query but its dispatcher gave up before producing a result, so the query exceeded the time budget the endpoint enforces rather than timeout_seconds. `overpass_unavailable`: Overpass answered with an HTTP 5xx other than 504 (500, 501, 502, 503) — the endpoint is down, restarting, or shedding load. The thrown code tracks the status: 500 and 501 surface as InternalError, every other 5xx as ServiceUnavailable. `endpoints_exhausted`: Every Overpass endpoint tried was still unanswered when the call ran out of its total time budget — each accepted the query and held the connection instead of failing outright. Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "invalid_tag",
      +            "query_timeout",
      +            "result_too_large",
      +            "rate_limited",
      +            "upstream_error",
      +            "overpass_gateway_timeout",
      +            "overpass_unavailable",
      +            "endpoints_exhausted"
      +          ],
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "elements",
      -  "attribution",
      -  "effectiveTag",
      -  "totalFound",
      -  "truncated"
      -]
  7. Changed2 schema fields changed
    • changedInput schema / properties / element_types / description
      Previous value: -"OSM element types to search. Ways cover most buildings and areas; nodes cover most standalone POIs. Add \"relation\" for complex structures like large campuses."New value: +"OSM element types to search, at least one. Ways cover most buildings and areas; nodes cover most standalone POIs. Add \"relation\" for complex structures like large campuses. Omit the field to search nodes and ways; an empty array is rejected because it can only match nothing."
    • addedInput schema / properties / element_types / minItems
      Added value: +1
  8. Changed1 schema field changed
    • addedInput schema / anyOf
      Added value: +[
      +  {
      +    "required": [
      +      "amenity"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "required": [
      +      "tag_key",
      +      "tag_value"
      +    ],
      +    "type": "object"
      +  }
      +]
  9. Changed1 schema field changed
    • addedOutput schema / properties / servingEndpoint
      Added value: +{
      +  "description": "Overpass endpoint that produced this response, as origin and path. Differs from the first configured endpoint when a mirror answered after the primary failed, and names the endpoint that served a cached response rather than the one this call would have tried. Pair it with data_timestamp when a result looks unexpectedly slow, sparse, or stale.",
      +  "type": "string"
      +}
  10. Changed2 schema fields changed
    • changedOutput schema / properties / data_timestamp / description
      Previous value: -"OSM data freshness timestamp from the Overpass response."New value: +"OSM data freshness timestamp from the Overpass response. Absent when the endpoint reported no freshness metadata."
    • changedOutput schema / required
      Previous value: -[
      -  "elements",
      -  "data_timestamp",
      -  "attribution",
      -  "effectiveTag",
      -  "totalFound",
      -  "truncated"
      -]New value: +[
      +  "elements",
      +  "attribution",
      +  "effectiveTag",
      +  "totalFound",
      +  "truncated"
      +]
  11. Changed1 schema field changed
    • changedOutput schema / properties / elements / items / properties / osm_id / description
      Previous value: -"OSM element ID. Use with osm_type for openstreetmap_lookup."New value: +"OSM element ID. Use with osm_type for openstreetmap_lookup_objects."
  12. Changed1 schema field changed
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when no features were found — e.g., try a larger radius or different tag. Absent when results were returned."New value: +"Guidance when the page came back empty. Distinguishes a query that matched nothing (try a larger radius or different tag) from an offset past the end of a non-empty result set (retry at a lower offset). Absent when results were returned."
  13. Changed3 schema fields changed
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Number of matching features to skip before applying limit, for paging through a large result set. Features are distance-sorted before paging, so higher offsets return progressively farther matches; the full set is cached ~10 minutes so re-paging costs no extra upstream request. Pass the nextOffset value from a prior truncated response.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / nextOffset
      Added value: +{
      +  "description": "Offset to pass on the next call to retrieve the following page of features. Present only when more features remain beyond this page.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / truncated / description
      Previous value: -"True if results were cut at the limit. Reduce radius or add more specific tags to narrow the result set."New value: +"True if results were cut at the limit. Reduce radius, add more specific tags, or page with offset to retrieve the rest."
  14. Changed5 schema fields changed
    • addedOutput schema / properties / effectiveTag
      Added value: +{
      +  "description": "The OSM tag filter applied (key=value, e.g. \"amenity=cafe\" or \"leisure=park\").",
      +  "type": "string"
      +}
    • addedOutput schema / properties / notice
      Added value: +{
      +  "description": "Guidance when no features were found — e.g., try a larger radius or different tag. Absent when results were returned.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / totalFound
      Added value: +{
      +  "description": "Total features returned by Overpass before limit truncation.",
      +  "type": "number"
      +}
    • removedOutput schema / properties / total_found
      Removed value: -{
      -  "description": "Total features returned by Overpass before limit truncation.",
      -  "type": "number"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "elements",
      -  "total_found",
      -  "truncated",
      -  "data_timestamp",
      -  "attribution"
      -]New value: +[
      +  "elements",
      +  "data_timestamp",
      +  "attribution",
      +  "effectiveTag",
      +  "totalFound",
      +  "truncated"
      +]
  15. Changed1 schema field changed
    • addedOutput schema / properties / elements / items / properties / distance_meters
      Added value: +{
      +  "description": "Great-circle distance in meters from the query center, rounded to one decimal. Results are sorted ascending by this value; omitted for elements without a computed coordinate.",
      +  "type": "number"
      +}
  16. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safe/read-only nature is covered. The description adds valuable behavioral details: every feature returns with its full OSM tag set (no extratags flag), results are sorted nearest-first by distance_meters, and nodes cover standalone POIs while ways cover buildings/areas. This goes beyond the annotations and schema, providing concrete expectations about output ordering and content.

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 description is compact—two sentences—and front-loads the core purpose before adding filtering and result details. Every sentence contributes actionable information: the query type, filter combination, output completeness, sorting, and element-type coverage. No redundancy or filler.

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?

Given the tool's complexity (11 parameters, output schema present, and 100% schema coverage), the description adequately covers the high-level behavior: the primary filter modes, optional filters, result ordering, and element-type semantics. It does not cover pagination or timeout details, but those are already in the schema. The description is sufficient for an agent to understand the tool's role and invoke it correctly.

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?

The input schema has 100% description coverage for all parameters, so the baseline is 3. The description supplements this by explaining the primary filtering modes (amenity vs. tag_key), the ANDing of up to five additional filters, and the node/way coverage distinction. While helpful, it does not introduce critical meaning absent from the schema—the schema already documents each parameter thoroughly.

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 description clearly states the verb 'Find' and the resource 'OSM features within a radius of a point', and distinguishes itself as 'the tool for "what is near X?" questions'. This specificity separates it from sibling tools like query_bbox or search_places, making its purpose unambiguous.

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?

It explicitly frames the use case as proximity queries, saying 'the tool for "what is near X?" questions'. However, it does not name sibling tools or explicitly state when NOT to use it (e.g., for bounding-box queries), leaving some inference to the agent. The context is clear but alternatives are not directly mentioned.

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.