Skip to main content
Glama

DealLabs

Search verified places

search_verified_places
Read-only

Find places and stations by name, kind, category, area, nearness or opening time. Answers only from data-standard v1 records; null values are reported as not_known. It does not return train times: for a station's exits or its last trains, call get_station_exit with the station name.

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": {
      "city": "<city>"
    },
    "name": "search_verified_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNo
cityYesCity key, e.g. "seoul".
kindNoexit: give the station name in query; returns that station's exits.
nearNoSort by straight-line distance from {lat, lng} or from a station (name or place_id).
limitNo
queryNoMatched against name and name_local.
open_atNo
categoryNo
walk_maxNoMinutes on foot from the station (only records with a walk).
min_confidenceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare readOnlyHint, so the description carries the rest and does add real context: results are sourced exclusively from data-standard v1 records and nulls are surfaced as not_known, which tells the agent how to interpret gaps rather than treating them as absence. It omits pagination/limit behavior and what a result record looks like, so it is not fully self-sufficient.

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?

Two sentences, front-loaded with the capability, then the data-provenance caveat, then the redirect. Every clause carries information and nothing is repeated from the schema.

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 ten-parameter tool with a nested near object and no output schema, the description covers purpose, data provenance, null semantics, and the main exclusion/redirect. Gaps remain around result shape, limit/pagination behavior, and what min_confidence filters, so it is strong but not complete.

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 description names most filter facets in prose (name via query, kind, category, area, nearness, opening time), which maps onto six of the ten parameters. With schema coverage at 50%, the undocumented remainder — city, limit, min_confidence, and the walk-only constraint on walk_max — gets no compensating explanation beyond what the schema fragments already say.

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 and resource ('Find places and stations') plus the facets it searches across (name, kind, category, area, nearness, opening time), and explicitly names a sibling it is not ('It does not return train times ... call get_station_exit'). An agent can distinguish it from get_station_exit without opening either schema.

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?

Provides an explicit when-not with a named alternative and the argument to pass ('call get_station_exit with the station name'), which is exactly the routing an agent needs for the station-exit case. It gives no guidance for the other siblings, and the overlap between kind="popup"/"event" and find_active_popups is left unresolved.

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