Skip to main content
Glama

경매가 vs 실거래 시세 비교

realty_compare_auction_vs_market
Read-onlyIdempotent

경매 물건의 최저입찰가를 같은 단지 실거래 시세와 대조해 할인율·표면수익률을 낸다. 기본은 오늘 이후 기일 물건만이다(지난 기일이 섞여 나오던 결함 수리, 2026-08-08).

주소·단지명 정규화 정확매칭으로 붙이며, 감정가가 기준선의 50~150% 범위인 건만 비교한다
(지분경매·특수물건을 배제하기 위함). 결과의 `signal`은 주의/관심/보통/낮음/판정보류다.
**시세 기준선은 같은 단지의 같은 면적대(±10%) 실거래 평균이다**(2026-08-16 수리 — 종전엔
단지 전 평형 혼합 평균이라 대형·소형이 섞인 단지에서 할인율이 통째로 어긋났다).
면적을 맞추지 못하면 `discount_vs_market_pct`는 **null**이고 signal은 '판정보류'다 —
그 자리를 `discount_vs_all_types_pct`(혼합평균 대비)로 대신 채워 말하지 마라.
⚠️ 유찰 물건은 `auction.min_bid_source`를 확인하라 — item_list면 최저가가 낡았을 수
있고(`min_bid_note` 동봉) 그 최저가로 계산된 할인율·수익률도 함께 틀어진다.
이 도구는 다른 도구보다 느리다(출처 조회 포함 2~4초).

**이 축의 자리(경매 가격판단 3종 중)**: "이 물건 싸?"는 이게 1차다(시세 자동 조인).
입찰가 책정은 realty_auction_sale_rate(감정가 대비 실제 낙찰가율)와 함께 쓰되,
이 도구의 할인율(시세 대비)과 낙찰가율(감정가 대비)은 **분모가 달라 섞으면 안 된다**.
기준 시세를 손으로 잡을 땐 realty_area_price_bands(수준)/region_price_stats(추이).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sidoNo시도 — '서울'처럼 줄여 써도 되고 '서울특별시'도 된다(서버가 정식명으로 편다). 원장 표기는 서울특별시·경기도·부산광역시·세종특별자치시·강원특별자치도 같은 정식명이다. '광주'는 광주광역시와 경기도 광주시 둘 다라 한쪽으로 읽지 않는다 — 정식명으로 넣어라
limitNo비교할 물건 수 (최대 50) (허용 범위 1~50)
case_noNo특정 사건 하나만 비교할 때 — `2026타경3571` 꼴(연도 4자리 + '타경' + 일련번호). 주면 지역 조건 대신 이 사건만 보고, 기일 제한도 걸지 않는다. 사건번호는 법원 간 중복되니 court_name을 반드시 함께 주라
sigunguNo시군구 — 원장 표기 그대로 넣는다(예: '강남구', '평택시', '기장군'). 특례시·일반구는 '수원시 권선구'처럼 두 토막이다. 시도 이름을 여기 붙이지 마라('서울 강남구'는 안 맞는다) — 시도는 sido로 준다
court_nameNo법원명 — case_no와 함께 쓴다. 사건번호는 법원 간 유일하지 않아(평균 2.8배 중복) 이걸 빼면 다른 법원 물건이 섞이고 최저가 출처도 확정되지 않는다
usage_nameNo물건 종류 — 이 도구는 같은 단지 실거래와 붙이므로 '아파트'가 기본이다. 오피스텔·다세대·연립주택도 되지만 단지 매칭률이 떨어진다. 원장 값 예: 아파트·오피스텔·다세대·연립주택·단독주택·근린시설·상가아파트
include_pastNo지난 기일 물건 포함 여부 — 기본은 오늘 이후 기일만(입찰 가능 후보). case_no 특정 조회는 이 값과 무관하게 기일 제한이 없다

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds substantial beyond-that value: slow execution (2~4s), exact complex matching, 50~150% appraisal filter, same-area ±10% baseline logic, null/판정보류 behavior, and the warning that 유찰 items may have stale minimum bids via min_bid_source. These are non-obvious behavioral traits an agent needs before invoking.

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?

The description is longer than average but dense and structured: core purpose first, then matching rules, then score semantics, then warning notes about stale bids and slow execution, then sibling-tool positioning. Each sentence carries a distinct operational or interpretational fact, including caveats that would otherwise require a second query.

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 and no required parameters, the description carries the full interpretational burden and does so well: it explains signal values, null discount, fallback discount field, min_bid_note, data-matching limitations, and related-tool routing. The agent has enough context to invoke the tool correctly and interpret the response without additional discovery.

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?

The input schema describes all 7 parameters thoroughly, so the baseline is 3. The description mostly restates schema-level points such as the default today-or-later auction dates and case_no bypassing date restrictions, and its real added value is about output behavior rather than input parameter semantics. It does not materially raise the semantic clarity of any parameter.

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 states a specific action: compare an auction property's minimum bid against same-complex actual transaction prices and produce 할인율·표면수익률. It also distinguishes itself from the related auction pricing tool realty_auction_sale_rate by noting the different denominators, so an agent can select it without opening the sibling schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit routing guidance: use this tool first for '이 물건 싸?', pair it with realty_auction_sale_rate for bid pricing, and switch to realty_area_price_bands/region_price_stats when manually choosing a baseline. It also explains the default date filter and that a case_no query bypasses the date restriction, making the choice of parameters and tools clear.

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.

TDQS

A3.9/5.0
Disambiguation3/5

The set has very explicit cross-tool guidance and each tool is often given a specific 'role', but there are still many overlapping clusters: auction search vs auction list vs auction detail, regional price bands vs price stats vs rankings, and court auction rate vs public auction rate. The descriptions reduce misselection, but with 51 tools including pairs like `fetch` and `realty_get_auction_case`, confusion is still likely for an agent.

Naming Consistency4/5

Most tools follow a clean `realty_` prefix and use consistent snake_case noun-phrases or verb-noun patterns, e.g. `realty_search_auctions`, `realty_get_auction_case`, `realty_presale_cost`. The exceptions are the generic `fetch`, `search`, and `report_issue`, which break the uniform prefixed convention but are only a small minor deviation from an otherwise consistent naming system.

Tool Count1/5

51 tools far exceeds the recommended threshold, even for a deliberately broad real-estate area; it is effectively an extreme number for a single MCP server. The tool count becomes the hardest usability problem, since agents must handle many tightly related micro-tools instead of interacting with a smaller, more manageable surface.

Completeness5/5

The tool set covers an impressively complete range: auction and public-auction workflows, apartment and non-apartment market, presale/cheongyak processes, tax and loan rules, subscription scoring, redevelopment, demographics, supply, POI, and even a reporting and routing tool. Boundaries and unsupported cases are explicitly documented, so there are no major obvious dead ends.