Skip to main content
Glama
Sign In
geo-figure-mcp

geo-figure-mcp

by skyblue3925-svg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

find_data

Fetch real statistics with sources and years from World Bank, OWID, KOSIS, climate, and regional datasets for charts and maps. Use only returned figures, not invented numbers.

Instructions

실제 통계를 찾는다. 결과에 출처(cite)와 연도가 붙는다. 숫자를 지어내지 말고 이 결과만 쓴다.

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": {
      "source": "<source>"
    },
    "name": "find_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNo특정 연도. 비우면 가장 최근
kosisNosource 가 kosis 일 때: { orgId, tblId, itmId, objL1:"ALL", objL2, year }
yearsNotrue 면 연도별 전체(시계열)
bundleNosource 가 bundle 일 때: { key, items:[항목], period, where:{ C1:"총인구" } }
sourceYes자료원
regionsNo나라 ISO3(KOR, JPN…, 세계=WLD) / 기후: 기출 지점 한글 이름·관측소 영문 이름·"위도,경도" / 서울 자치구 이름
indicatorsNo지표 코드 또는 열 이름

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that every result is tagged with a citation and year, which is valuable given there is no output schema, but it omits auth requirements (kosis clearly needs a key per set_kosis_key), rate limits, and per-source failure behavior for a 7-source tool.

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?

Three short sentences with the purpose front-loaded and no filler. The citation/anti-fabrication rules follow logically and every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 7 parameters, nested objects, and 7 enum sources, the description covers purpose, output tagging, and the no-hallucination rule, with the schema handling parameter detail. It still leaves source-selection guidance and auth prerequisites unstated, which matters for a tool spanning worldbank, kosis, bundle, and climate backends.

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 description coverage is 100%, so the schema already documents source, regions, indicators, year/years, and the nested kosis/bundle shapes with examples. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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?

The description gives a concrete verb+resource ("실제 통계를 찾는다" = finds actual statistics) that tells an agent this retrieves real data rather than metadata. However, it does not differentiate from siblings like kosis_search or list_sources, leaving the boundary between searching for a table and fetching its values unstated.

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?

"숫자를 지어내지 말고 이 결과만 쓴다" is a clear directive to use the returned values rather than fabricate, which implies when this tool is appropriate. But there is no explicit when/when-not guidance and no routing to alternatives such as kosis_search or list_sources, so selection against siblings is left to inference.

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

Deploy Server

Other Tools