Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

geocoding_search

Search OpenStreetMap places by free-text query or structured address fields and get coordinates, categories, and address details for location lookups.

Instructions

Search Nominatim places. Searches OpenStreetMap places by address. Pass either free-text q or structured fields (street, city, county, state, country, postalcode), not both. limit defaults to 10 and is clamped to 20; countrycodes restricts by ISO 3166-1 alpha-2 country. Each result has its display name, coordinates, category, type, bounding box, importance and address parts. No match returns 404.

Input Schema

NameRequiredDescriptionDefault
qNoFree-text search query
cityNoStructured city
limitNoMaximum results, defaults to 10 and clamps to 20
stateNoStructured state
countyNoStructured county
streetNoStructured street or house number
countryNoStructured country
extratagsNoInclude OSM extra tags
postalcodeNoStructured postal code
namedetailsNoInclude multilingual name details
countrycodesNoComma-separated ISO 3166-1 alpha-2 country filters
addressdetailsNoInclude address details, defaults to true
accept_languageNoPreferred result language, forwarded to Nominatim

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does meaningful work: it discloses limit clamping (20), the 404 no-match behavior, countrycodes ISO 3166-1 alpha-2 filtering, and the result shape. It omits operational traits Nominatim is known for (rate limits, no auth), which keeps it from a 5.

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?

Front-loaded with the core purpose, then constraints, then return/error behavior. Every sentence carries information — no filler, no restatement of the name.

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?

No output schema exists, so the description correctly summarizes return fields (display name, coordinates, category, bounding box, importance, address parts) and the 404 case. The remaining gap is operational caveats (rate limits) that an agent calling a public Nominatim endpoint would benefit from knowing.

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 adds value beyond the schema by stating that `q` and the structured fields are mutually exclusive — a constraint absent from the schema. It also restates limit default/clamp and countrycodes format, reinforcing key params.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: search OpenStreetMap/Nominatim places by address. An agent can distinguish it from geocoding_reverse (reverse lookup) by the 'by address' framing. It does not explicitly name a sibling, so it lands at 4 rather than 5.

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

Usage Guidelines3/5

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

Gives an important input-mode constraint (use `q` or structured fields, not both), which is real usage guidance for calling it. However, it offers no when-to-use/when-not selection logic against alternatives like geocoding_reverse or the maps search tools, so usage is only implied at the tool-selection level.

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

Deploy Server

Other Tools