Skip to main content
Glama
syleedlabs

deal-locator-mcp

by syleedlabs

데이터카드 만들기

deal_card_create

Create a PNG data card from an address, showing actual transaction and building details: price, area, price per unit, zoning, year built, date, and match confidence badge.

Instructions

지번 하나로 실거래 데이터카드 PNG 1장(4:5)을 만든다 — 조회부터 이미지까지.

카드에 들어가는 값은 전부 실거래·건축물대장 실측값이다(매매가·토지/연면적· 평단가·용도지역·준공연도·거래일·매도매수). 홍보 문구는 넣지 않는다.

매칭 신뢰도가 카드에 배지로 찍힌다. 이미지가 손을 떠난 뒤에는 대화로 고지할 수 없기 때문이며, '추정매칭' 이하는 색으로 구분된다. 고객에게 내밀기 전에 match_explain 으로 근거를 확인시키는 걸 권한다.

사진이 없으면 렌더하지 않고 PHOTO_MISSING 으로 멈춘다 — 카드는 건물 사진 위에 수치를 얹는 형태라, 사진이 없으면 회색 판이 나가고 결국 다시 만들게 된다. 이때는 재시도하지 말고 사용자에게 사진 경로를 물어볼 것. 사진 없이 진행하기로 사용자가 정하면 allow_no_photo=true 로 재호출한다. eyebrow 로 매매가 위 골드 한 줄을 덮어쓸 수 있다. 기본값은 '<구> 실거래 · YYYY.MM'. '최고가/최저가' 같은 단정 표현은 쓰지 말 것 — 이 도구의 조회 범위(서울 상업업무용·기간 한정) 안에서의 순위일 뿐이라 카드에 박히면 근거 없는 단정이 된다. 저장 위치는 ~/deal-locator-cards/<날짜>/ (DEAL_LOCATOR_CARD_DIR 로 변경 가능).

최초 1회 playwright install chromium 이 필요하다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
photoNo
monthsNo
addressYes
eyebrowNo
allow_no_photoNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsYes
notesNo
photoNo카드에 쓴 건물 사진(미지정 시 빈 문자열)
priceNo
queryYes
sourceYes
statusYesOK 일 때만 out_png 에 카드가 생성됐다. PHOTO_MISSING 은 실패가 아니라 '사람이 결정할 게 남은' 상태 — 사진 경로를 주거나 allow_no_photo=true 로 재호출하면 진행된다.
addressNo
eyebrowNo
messageNo
out_pngYes생성된 카드 PNG 경로(4:5, 2160×2700)
confidenceNo
confidence_scoreNo
Behavior5/5

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

The description transparently discloses key behaviors: creation of a PNG (mutation, consistent with readOnlyHint=false), confidence badge rendering, photo requirement causing PHOTO_MISSING failure, and restriction against promotional wording. This adds context beyond the annotations (which only hint at non-readonly and open-world).

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 moderately concise; all sentences add value but the second paragraph could be trimmed. It is front-loaded with the main purpose and key constraints. Minor redundancy in explaining the photo failure mode.

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?

Given 5 parameters, a non-trivial operation, and the existence of an output schema, the description covers the essential workflow, failure modes, and output type. It lacks explicit return value documentation but the output schema fills that gap. Months parameter explanation is missing, slightly reducing completeness.

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?

With 0% schema description coverage, the description must explain parameters. It does well for address, eyebrow, and allow_no_photo, but months and photo are only implicitly mentioned (months as '기간 한정', photo as required). The description partially compensates but leaves some parameters insufficiently explained.

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 description clearly states the tool's purpose: creating a PNG card (4:5 ratio) with real transaction data from a land lot number. It distinguishes itself from sibling tools like deal_card_search and deal_history by specifying the one-to-one mapping from address to card image.

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 provides explicit when-to-use guidance: recommending use of match_explain before presenting the card, handling photo missing by asking user for photo path or allow_no_photo=true, and prohibiting assertive phrases like '최고가/최저가' in the eyebrow. Also notes the one-time prerequisite 'playwright install chromium'.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/syleedlabs/deal-locator-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server