Skip to main content
Glama

주변 정류소 찾기

find_nearby_stops

Find nearby bus stops by latitude and longitude, sorted by distance, without requiring a city code. Results include the city code for each stop.

Instructions

위도·경도 주변의 버스 정류소를 가까운 순으로 찾습니다(distanceM: 미터). 도시 코드가 필요 없고, 결과에 cityCode가 포함됩니다. 같은 정류소가 인접 도시 시스템에 중복 등록되어 cityCode만 다르게 두 번 나올 수 있습니다.

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>",
      "lng": "<lng>"
    },
    "name": "find_nearby_stops"
  }
}

Input Schema

NameRequiredDescriptionDefault
latYes위도. 예: 36.3511
lngYes경도. 예: 127.3848
limitNo최대 결과 수

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses result ordering (nearest first), result field units (distanceM in meters), the presence of cityCode in output, and a non-obvious data quirk — duplicate stops from adjacent city systems appearing twice with different cityCode. It omits any statement about rate limits, error behavior for coordinates outside the allowed bounds, or how limit truncation is reflected.

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?

Three compact sentences, each carrying distinct information: what it does and its ordering, the city-code-free behavior and returned field, then the duplication caveat. The core action is front-loaded and nothing is redundant.

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?

There is no output schema, so the description must cover returns, and it does address ordering, distanceM, and cityCode as well as the duplicate-result caveat. The remaining gap is that it does not say how 'limit' affects the response (e.g., truncation without indication of total matches), which matters for an agent deciding whether to widen the limit.

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

Parameters5/5

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

Schema description coverage is 100%, so the schema already documents lat, lng with examples and limit with bounds and default; the baseline would be 3. The description adds genuine meaning on top by clarifying the spatial relationship between lat/lng and returned stops and by explaining that no city code parameter is needed — a real semantic point the schema cannot convey.

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 ('위도·경도 주변의 버스 정류소를 가까운 순으로 찾습니다') plus the sort order and the distanceM unit. It implicitly separates itself from name-based or route-based siblings by noting no city code is required, but it never names the sibling it replaces, so differentiation is left to inference.

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?

The '도시 코드가 필요 없고' clause tells the agent this is the right choice when no city code is known, which is real usage context. However, there is no explicit when-not guidance and no named alternative such as search_bus_stops for name-based lookup, so the agent must guess which sibling handles those cases.

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