Skip to main content
Glama
Sign In

korea-realty

by app.sallim
OverviewDiscussionsAdmin

빈집(미거주주택) — 시군구 빈집 수·비율·건축연도·원인 유형

realty_vacant_housing
Read-onlyIdempotent

통계청 빈집(미거주주택) — 빈집 수·빈집 비율·전체 주택, 아파트/비아파트, 건축연도 구간, 원인 유형.

"○○ 빈집 몇 채야", "빈집 왜 늘었어", "빈집률 높은 시", "과천 빈집", "지방 빈집"류 질문의 자리다.
시군구를 주면 연도 시계열(2015~)·아파트/비아파트 분리·건축연도 구간(최근 2년 준공·1980년대·1979 이전 등)·
재고 대 세대 증감 분해·준공후 미분양 몫·**같은 유형(시·구·군) 안 백분위**·원인 유형 라벨
(정비사업 이주형·공급·입주형·인구유출·노후형·관광·세컨드형(추정), 규칙과 근거 수치 동봉)을 준다.

**결론에 반드시 옮길 것**:
· `definition` — 통계청 미거주주택은 조사 시점(11월 1일) 비어 있는 집 전부(매매·이사 대기·미분양 포함)이고
  **법정 빈집(1년 이상 미사용)과 다르다.** 지자체 법정 빈집 실태조사 수치는 이 도구에 없다.
· 빈집 수(vacant_housing_count)와 빈집 비율(vacancy_rate_pct)을 섞지 마라.
· 원인 유형은 우리 규칙의 라벨이고, 빈집률로 가격을 내다보지 마라 — 같은 기간 동행 관측만 있다
  (meta.findings_not_prediction).
· null 값은 0이 아니다 — null_reasons(KOSIS 비공개 'X' 등)를 옮겨라.

Input Schema

NameRequiredDescriptionDefault
limitNo순위·하위 지역 행 수 (허용 범위 1~60)
regionNo'전국'·시도('경기')·시군구('과천시', '서울 중구'). 동명 시군구는 시도를 붙여라 — 안 붙이면 후보를 돌려준다. 구가 있는 시(수원·성남 등)는 시 단위만 있다. rank_by로 순위를 볼 땐 비워 둔다
rank_byNoregion 없이 순위를 볼 때 — 같은 area_type 안에서만 정렬한다(빈집률·빈집 수·5년 빈집률 변화)
area_typeNo순위의 유형 — rank_by와 함께 필수. 시·구·군을 섞은 순위는 내지 않는다

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial behavioral context on top: the definitional caveat that 통계청 미거주주택 ≠ 법정 빈집, that count and rate must not be conflated, that cause labels are rule-based not predictive (meta.findings_not_prediction), and that null is not zero (null_reasons/KOSIS 'X'). This is exactly the extra disclosure the rubric rewards.

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?

Purpose is front-loaded, and the metrics returned are given as a scannable list before the '결론에 반드시 옮길 것' caveats. It is dense and fairly long, with some overlap between the return-value list and the caveat block, but each section carries distinct information rather than filler.

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

Completeness5/5

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

With no output schema, the description must carry the burden of return semantics, and it does: time-series range (2015~), apartment/non-apartment split, building-year brackets, decomposition, percentile, and cause labels. Combined with the null and definition caveats, an agent has everything needed to call and interpret the tool.

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 all four parameters (limit, region, rank_by, area_type) are already documented, including enum semantics and the region+rank_by interaction. The description adds no parameter syntax or format detail beyond the schema, so the baseline 3 is correct.

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 names a specific data source (통계청 빈집/미거주주택) and enumerates the exact metrics delivered — 빈집 수, 빈집 비율, 전체 주택, 아파트/비아파트, 건축연도 구간, 원인 유형 — so the resource is unambiguous. It also distinguishes its scope from the 지자체 법정 빈집 실태조사, but never names a sibling tool, so it falls short of the 5-level sibling differentiation.

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?

Concrete trigger phrasings ('빈집 몇 채야', '빈집 왜 늘었어', '빈집률 높은 시', '과천 빈집') make the intended question space clear. It also states what the tool does NOT cover (법정 빈집 실태조사 수치). However it never routes the agent to an alternative tool or states an explicit when-not-to-use boundary against siblings such as region_rankings.

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

All korea-realty toolsInspect
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