Skip to main content
Glama

Search places and addresses

bl_search
Read-onlyIdempotent

Search Iranian places, streets, neighborhoods, cities, and addresses by name; returns coordinates and address details, and geocodes city names or addresses.

Instructions

Search Balad (Iranian map) for places, streets, neighbourhoods and cities by name, with coordinates and address.

Also geocodes addresses and city names. Pass lat/lng when searching outside Tehran (nearer results rank first). type is poi (pass its id to bl_place), road, city, region or category (its category slug goes to bl_nearby). For all places of one kind use bl_nearby. Empty: try a shorter or Persian query.

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": "bl_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude to search around. Default: Tehran.
lngNoLongitude to search around. Default: Tehran.
limitNoMax results (1-20).
queryYesPlace name, street, address, neighbourhood or city, e.g. برج میلاد.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.2.0
    • changedInput schema / properties / lat / description
      Previous value: -"Latitude to search around, e.g. 29.6100. Default: Tehran."New value: +"Latitude to search around. Default: Tehran."
    • changedInput schema / properties / lng / description
      Previous value: -"Longitude to search around, e.g. 52.5383. Default: Tehran."New value: +"Longitude to search around. Default: Tehran."
    • changedInput schema / properties / query / description
      Previous value: -"What to find, in Persian or English: a place name, street, address, neighbourhood or city, e.g. برج میلاد or خیابان ولیعصر."New value: +"Place name, street, address, neighbourhood or city, e.g. برج میلاد."
  2. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered elsewhere. The description adds behavior the annotations cannot: Tehran is the default search centre, proximity affects ranking order, and empty result sets should trigger a query rewrite. It does not say how results are ordered or capped beyond the schema's limit, but that is a minor gap given annotation coverage.

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?

Dense but front-loaded: capability, geocoding, ranking caveat, sibling routing, then failure recovery. No filler sentences, and every clause carries information except the `type` passage, which is wasted and misleading. The telegraphic phrasing occasionally reads as cryptic but stays parseable.

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?

For a 4-parameter read-only search with no output schema, the description covers what is returned, the default location, ranking behavior, and sibling hand-offs. The one substantive incompleteness is the phantom `type` parameter, which leaves the agent unsure whether kind-filtering is available here or only via bl_nearby.

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

Parameters2/5

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

Schema coverage is 100%, so baseline is 3, and the description does add the useful 'lat/lng outside Tehran changes ranking' nuance. However, it repeatedly instructs the agent to use a `type` parameter ('`type` is poi ... road, city, region or category') that does not exist in the input schema, which would lead an agent to pass an invalid argument. Misdescribing the parameter surface is worse than saying nothing.

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 Balad ... for places, streets, neighbourhoods and cities by name') plus the return payload ('with coordinates and address') and a secondary capability (geocoding addresses and city names). An agent can distinguish this place/address lookup from bl_reverse_geocode and bl_nearby purely from the text.

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 routing: pass lat/lng when searching outside Tehran, send a poi `id` to bl_place, send a category slug to bl_nearby, and use bl_nearby for 'all places of one kind'. It also prescribes a recovery path on empty results (shorter or Persian query), so when-to-use, when-to-hand-off and failure handling are all covered.

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