Big Data Insights for Regional Inflow in Korea

get_weather

시군구의 주차별 날씨를 돌려준다. 나우캐스트 이동량과 같은 주차(월~일, 'YYYY.MM.N주차')로 묶여 있다. - 값: ta_avg 주 평균기온(°C), ta_max 주 최고기온, ta_min 주 최저기온, rn_sum 주 강수량 합계(mm), rain_days 1mm 이상 비 온 날 수, sd_max 주중 최심 적설(cm), days 관측된 날 수. - 날씨는 시군구가 아니라 관측소 값이다. 관측소가 없는 시군구는 인근 관측소 값을 빌려 쓰므로 결과의 '관측소'와 '짝지은 방식'을 답에 함께 밝힐 것. 산간·해안처럼 관측소와 환경이 다른 곳은 오차가 있다. - 날씨와 이동량을 함께 볼 때, 같은 시기에 명절·연휴·행사가 겹쳤는지 먼저 확인할 것. 비 온 주에 이동이 줄었다고 해서 비가 원인이라고 단정하지 말고 가설로 표현할 것.

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": {
      "sigungu": "<sigungu>",
      "sido": "<sido>",
      "start_week": "<start_week>",
      "end_week": "<end_week>"
    },
    "name": "get_weather"
  }
}

Input Schema

Name	Required	Description	Default
`sido`	Yes
`sigungu`	Yes
`end_week`	Yes
`start_week`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A4.3/5.0

Behavior5/5

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

The definition discloses behavior that annotations do not cover: weather values come from observation stations, not sigungu boundaries; sigungu without a station borrow nearby stations and may carry error in mountainous or coastal areas; and the answer must state the '관측소' and '짝지은 방식' used. It also enumerates every returned field with units (°C, mm, cm) even though no output schema exists.

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 description is front-loaded with purpose, then bulleted field values and caveats, and every clause is informative. The closing advice on causal inference is slightly long for a data-retrieval tool, but it is actionable and earns its place.

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?

With no annotations and no output schema, the definition carries the full burden and mostly meets it: return fields, units, provenance, and week alignment are all covered. What remains is how to resolve values for sido and sigungu and how missing or out-of-range weeks behave.

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 explain all four required parameters. It only partly compensates: it pins down the 'YYYY.MM.N주차' week format and the Monday–Sunday boundary for start_week and end_week, but says nothing about the accepted values for sido and sigungu, such as whether to use list_regions codes or full Korean names.

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 first sentence names a specific verb and resource (weekly weather by sigungu) and immediately states its scope: weeks aligned to the nowcast movement tool's Monday–Sunday 'YYYY.MM.N주차' convention. This clearly distinguishes it from get_movement and get_breakdown without opening any 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 concrete usage context, telling the agent to use it alongside movement data and to check for holidays or events before attributing a drop in movement to rain, and to phrase such claims as hypotheses. It never names an explicit alternative for non-weekly or non-weather data (for example, get_datalab_daily), so it stops short of full routing guidance.

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

All Big Data Insights for Regional Inflow in Korea tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?