Skip to main content
Glama

FRNC — Korean Franchise Disclosure Risk Check

프랜차이즈 리스크 체크

check_franchise_risk
Read-only

브랜드·업종·가맹비·인테리어 비용과 본부가 제시한 조건(정보공개서 수령 후 경과일, 예상매출 서면 교부, 가맹금 예치·납부 방식, 인테리어 지정, 영업지역, 폐점률, 법 위반 이력, 필수품목 단가 공개 여부, 판매가격·할인 구속 여부 등)을 받아 위험 신호·확인 체크리스트·가맹사업법 조문 근거를 돌려줍니다. 판정은 check_likely(확인 필요 신호 있음) / info_needed(정보 부족) / low_risk(뚜렷한 위험 신호 없음) 세 가지이며 확정 판정이 아닙니다. 입력하지 않은 항목은 '모름'으로 두고 questions_ko 로 되물어봅니다. 창업비용을 낸 뒤 받을 수 있는 지원금은 GRNT(https://grnt-kr.onrender.com/)에서 확인하도록 startup_support 에 링크를 함께 돌려줍니다.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_franchise_risk"
  }
}

Input Schema

NameRequiredDescriptionDefault
industryNo업종(예: 치킨, 커피, 편의점)
other_krwNo기타 비용
territoryNo영업지역: exclusive(독점 기재) · defined(기재만) · none(없음) · unknown
brand_codeNo브랜드관리번호(아는 경우)
brand_nameNo브랜드명(예: 샘플치킨)
deposit_krwNo가맹보증금
penalty_krwNo위약금 액수(비율 대신 줄 때)
interior_krwNo인테리어 비용
price_fixingNo본부가 판매가격을 정하고 지키게 하는지
sales_targetNo판매목표 강제 여부
stores_countNo가맹점 수
avg_sales_krwNo가맹점 평균매출액
equipment_krwNo설비·집기 비용
payment_routeNo가맹금 납부 방식: escrow(예치기관) · insurance(피해보상보험) · hq_account(본사 계좌 직접 송금) · none(예치·보험 없음) · unknown
renewal_yearsNo최초 계약을 포함한 전체 계약기간(년)
ad_cost_burdenNo광고·판촉비 부담: shared(분담) · franchisee_forced(점주 의무) · none · unknown
legal_violationNo본부의 공정위 시정조치·과징금·형벌선고 이력 여부
renewal_refusedNo갱신 거절 사유가 넓은지
revenue_writtenNo매출 관련 정보를 서면으로 받았는지
advisor_reviewedNo변호사·가맹거래사 자문 여부(자문 시 숙고기간 7일)
revenue_claim_koNo본부가 한 매출 관련 말(예: '월 5천 보장')
royalty_rate_pctNo월 로열티 비율(%)
education_fee_krwNo가맹교육비
franchise_fee_krwNo가맹비(원 또는 '3,300만원')
penalty_ratio_pctNo중도해지 위약금 비율(총투자 대비 %)
discount_forbiddenNo할인 판매를 금지·제한하는지
mandatory_purchaseNo필수품목 구입 의무 여부
resale_price_boundNo본부가 정한 판매가격을 유지·준수하게 하는지(재판매가격 구속)
closure_rate_3y_pctNo최근 3년 폐점률(%)
interior_designatedNo인테리어 지정: free(자유) · partial(일부 지정) · forced(100% 강제) · unknown
supplier_designatedNo거래처(물품 공급처) 지정 여부
revenue_estimate_docNo예상매출액 산정서(범위·산출근거)를 받았는지
total_investment_krwNo총 창업비용(없으면 항목 합계로 계산)
disclosure_registeredNo등록 정보공개서를 확인했는지
essential_items_broadNo가맹사업과 무관한 일반 공산품까지 필수품목으로 지정했는지
disclosure_days_beforeNo정보공개서를 받은 날부터 계약(예정)일까지 지난 일수. 당일이면 0.
essential_price_hiddenNo필수품목 품목별 공급가격·산정기준을 알려주지 않았는지
margin_raise_unilateralNo차액가맹금(적정 도매가격을 넘는 대가)을 일방적으로 올렸는지
contract_doc_days_beforeNo가맹계약서 초안을 받은 날부터 경과일
termination_grace_monthsNo본부의 해지 시 유예기간(개월)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint/destructiveHint, the description discloses the three-tier output vocabulary (check_likely / info_needed / low_risk) and explicitly cautions that the result is not a final ruling — critical framing for how an agent should relay it. It also explains the fallback behavior for omitted parameters ('unknown' plus regenerated questions) and that a startup_support link is appended to the response. This is behavior an agent could not infer from annotations or schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and verdict vocabulary are front-loaded, which is correct, but the long parenthetical enumerating roughly a dozen input conditions largely restates what the 100%-covered schema already documents. Given 40 fully described properties, that clause spends words without adding meaning. The remaining sentences earn their place.

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?

For a 40-parameter, zero-required, no-output-schema analysis tool, the description supplies what the schema cannot: the shape of the response (risk signals, confirmation checklist, statutory citations), the verdict enum, the missing-input handling, and the appended subsidy link. An agent has everything needed to call it with partial data and to interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% across 40 parameters, so the baseline is 3, but the description adds a genuinely useful semantic rule the schema does not state: any parameter the caller omits defaults to 'unknown' rather than failing validation, since nothing is required. It also groups the inputs conceptually as HQ-presented conditions versus cost figures. It adds no per-parameter format guidance (e.g., accepting '3,300만원' strings), which keeps it from a 5.

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 verb-and-resource pair ('franchise risk check') and enumerates the inputs it consumes (brand, industry, franchise fee, interior cost, HQ conditions such as disclosure-document elapsed days, escrow method, territory, closure rate) plus the three possible verdicts. That makes the operation unambiguous even against siblings like compare_franchise_terms or get_law_article. It stops short of a 5 because it never explicitly contrasts itself with those siblings, even though it overlaps them by returning legal article citations and brand condition analysis.

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 clearly frames how to use the tool with incomplete data — unentered items are treated as 'unknown' and turned into re-asking questions via questions_ko — and warns that the verdict is not definitive. It also routes a related need (post-fee subsidies) to an external site. It does not say when to prefer compare_franchise_terms, scan_contract_text, or lookup_brand_disclosure instead, so no exclusions or sibling routing are present.

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.