Skip to main content
Glama

Big Data Insights for Regional Inflow in Korea

forecast_festival

지역 축제가 열리는 주의 관외 유입이 평소보다 얼마나 늘지 '비공식 참고 예측'을 범위로 돌려준다.

- 축제 방문객 수(명)를 예측하지 않는다. 관외 유입 이동 건수의 상승률(%)이다. '명'으로 바꿔 말하지 말 것.
- festival_name을 비우면 그 지역의 축제 목록을 돌려준다. start_date·end_date(YYYY-MM-DD)에 올해 일정을 넣으면
  연휴·공휴일 겹침 경고를 붙인다.
- 결과의 범위는 '과거 둘 중 한 번'·'열 번 중 여덟 번은 이 안'으로 말하고, '신뢰구간·오차범위'라고 부르지 말 것.
- '예측: 하지 않음'이면 그 이유를 그대로 전하고 숫자를 지어내지 말 것.
- 예측값은 '비교군 대비' 상승률이다. '평소보다 몇 %' 또는 '평소의 몇 배'로 바꿔 말하지 말 것
  (평소 대비는 '참고: 지난 회차 평소 대비 평균'을 따로 인용할 것).
- 축제 질문에 직접 계산하지 말고 이 도구를 쓸 것. '작년보다 늘었나'처럼 지난 회차끼리 견주는 질문에도 쓸 것
  (결과의 '지난 회차' 표).
- 지난 회차가 없는(처음 여는) 축제면 비슷한 지역 축제들의 '낮은 신뢰도 참고 범위'를 돌려준다.

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": {
      "sido": "<sido>",
      "sigungu": "<sigungu>"
    },
    "name": "forecast_festival"
  }
}

Input Schema

NameRequiredDescriptionDefault
sidoYes
sigunguYes
end_dateNo
start_dateNo
festival_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it discloses the fallback for first-time festivals (low-confidence range from similar regional festivals), a distinct 'no prediction' outcome that must be reported with its reason and must not be filled with invented numbers, and holiday-overlap warnings when dates are supplied. Remaining gaps are operational (invalid region handling, response field layout), which keeps it below 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the bullets are individually scoped, each covering a distinct constraint. Several bullets govern output phrasing rather than tool selection, which makes the block longer than a pure selection aid needs to be, though those rules are genuine behavioral content.

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 five-parameter tool with no annotations and no output schema, the definition covers result interpretation (range framing, comparison baseline, the 'last occurrence' table) and edge cases well enough to prevent misuse. It is thin on the shape of the returned payload and on accepted region-name formats, which an agent still has to discover by calling.

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?

Schema coverage is 0%, so the description must compensate, and it partially does: emptying festival_name returns the region's festival list, and start_date/end_date accept YYYY-MM-DD and trigger holiday-overlap warnings. The two required parameters, sido and sigungu, get no format or vocabulary guidance at all, leaving the most load-bearing inputs under-specified.

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 opening line names a specific output: the forecast range for how much a region's out-of-region inflow rises during the week of a local festival. It immediately fences off the adjacent quantity ('not visitor counts; it is a percent rise in movement events'), so an agent can tell what this tool does and does not produce without opening the 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?

It gives an explicit directive to use this tool for festival questions instead of computing, and extends that to year-over-year style comparisons ('작년보다 늘었나'). It stops short of naming an alternative tool or stating an explicit when-not condition, so routing is clear in the positive direction only.

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