Skip to main content
Glama

Folsn Product Catalog

폴슨 상품 검색 / Search Folsn products

search_folsn_products
Read-onlyIdempotent

폴슨(folsn)이 네이버 스마트스토어에서 직접 파는 상품을 상품 이름·옵션(용량·수량·색상·모델 번호)으로 찾습니다. 결과마다 판매가(원)·배송비·묶음 수량과 개당 환산가·재고 상태·구매 주소·가격 기록 시각·출처를 따로 돌려줍니다. 다른 쇼핑몰 가격이나 전체 최저가는 돌려주지 않습니다. 검색어는 한국어 상품명(브랜드 + 제품명 + 용량·수량)이 가장 잘 맞고, 등록된 영어 브랜드·상품명도 일부 지원합니다. matchStatus=needs_clarification이면 clarificationFields에 더 정해야 할 옵션 종류(예: capacity·packCount·color)가 들어 있습니다. 결과가 없으면 hint에 검색 범위와 다시 찾는 방법이 들어 있습니다. 예: {"query": "쿤달 칫솔 16입", "limit": 5} Search products sold directly by Folsn on its own Naver Smart Store (Korea) by product name and option (volume, count, color, model number). Each result returns price in KRW, shipping fee, bundle quantity with unit price, stock status, purchase URL, the time the price was recorded, and the source as separate fields. It does not return other stores' prices or market-wide lowest prices. Korean product names (brand + product + volume/count) match best; selected English brand and product names also work. Unknown English words remain unchanged. When matchStatus is needs_clarification, clarificationFields names the option types that still need to be specified (for example capacity, packCount or color). When there are no results, hint explains the search scope and how to search again. Example: {"query": "클로란 피오니 샴푸 400ml", "limit": 5}

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": {
      "query": "<query>"
    },
    "name": "search_folsn_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo최대 결과 수(1~10) / max results
queryYes상품 이름·옵션 검색어 또는 sku / product name and options, or sku

Output Schema

NameRequiredDescriptionDefault
hintNo
queryYes
noticeNo폴슨(folsn)이 네이버 스마트스토어에서 직접 파는 상품만 담습니다. 가격·배송비는 표시된 기록 시각(priceRecordedAt, 원천 기록이 갱신된 시각)의 값이며 판매처에서 다시 확인한 값이 아닙니다. 구매 직전 가격과 다를 수 있습니다. 가격은 같은 구성(compositionKey: 용량·수량)끼리만 비교하세요. 품절 상품의 기록 가격은 현재 구매 가능한 가격이 아니며 재고를 별도로 확인한 시각은 제공하지 않습니다. / Folsn's own Naver Smart Store products only. Prices are values as of the shown record time (priceRecordedAt, when the source record was last updated), not re-checked at the store, and may differ at checkout. Compare prices only within the same compositionKey. A recorded price for an out-of-stock item is not a currently purchasable price; no separate stock verification time is provided.
resultsNo
matchStatusYes
resultCountYes
relatedResultsNo
clarificationFieldsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / $defs / FolsnOffer / properties / pricePosition
      Added value: +{
      +  "$ref": "#/$defs/PricePosition"
      +}
    • changedOutput schema / $defs / FolsnOffer / required
      Previous value: -[
      -  "name",
      -  "sku",
      -  "options",
      -  "priceStatus",
      -  "shippingDetails",
      -  "bundle",
      -  "availabilityStatus",
      -  "seller",
      -  "source"
      -]New value: +[
      +  "name",
      +  "sku",
      +  "options",
      +  "priceStatus",
      +  "shippingDetails",
      +  "bundle",
      +  "availabilityStatus",
      +  "seller",
      +  "pricePosition",
      +  "source"
      +]
    • addedOutput schema / $defs / PricePosition
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "폴슨 가격의 상대 위치만 담습니다(같음·구간·모름). 금액·판매처·출처는 없습니다. / Relative position of Folsn's delivered price only; no amounts, sellers or sources.",
      +  "properties": {
      +    "basis": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Basis"
      +    },
      +    "label": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Label"
      +    },
      +    "note": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Note"
      +    },
      +    "percentBand": {
      +      "anyOf": [
      +        {
      +          "enum": [
      +            "1-5",
      +            "5-10",
      +            "10-20",
      +            "20-50"
      +          ],
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Percentband"
      +    },
      +    "reason": {
      +      "anyOf": [
      +        {
      +          "enum": [
      +            "not_provided",
      +            "no_basis",
      +            "no_own_total",
      +            "stale_basis",
      +            "own_record_time_mismatch",
      +            "inconsistent"
      +          ],
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Reason"
      +    },
      +    "recordedAt": {
      +      "anyOf": [
      +        {
      +          "format": "date-time",
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Recordedat"
      +    },
      +    "sourceType": {
      +      "anyOf": [
      +        {
      +          "const": "price_comparison_observation",
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Sourcetype"
      +    },
      +    "status": {
      +      "enum": [
      +        "matches_lowest",
      +        "higher",
      +        "unknown"
      +      ],
      +      "title": "Status",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "status"
      +  ],
      +  "title": "PricePosition",
      +  "type": "object"
      +}
  2. Changed3 schema fields changed
    • changedInput schema / properties / query / examples
      Previous value: -[
      -  "생수 2L 12입",
      -  "쿤달 칫솔 16입"
      -]New value: +[
      +  "쿤달 칫솔 16입",
      +  "클로란 피오니 샴푸 400ml"
      +]
    • addedOutput schema / properties / hint
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Hint"
      +}
    • addedOutput schema / properties / relatedResults
      Added value: +{
      +  "items": {
      +    "$ref": "#/$defs/FolsnOffer"
      +  },
      +  "title": "Relatedresults",
      +  "type": "array"
      +}
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds behavior beyond them: the exact per-result fields returned (price in KRW, shipping, bundle quantity with unit price, stock, purchase URL, price timestamp, source), the needs_clarification matchStatus contract with clarificationFields, and the no-results hint behavior. That is substantive edge-case and response-shape context on top of the safety profile.

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?

Each language version is well front-loaded — purpose first, caveats, then edge-case contracts, then an example. However the description is a full parallel duplication of Korean and English text, roughly doubling length, and the return-field list partly overlaps what the output schema likely already documents.

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?

For a two-parameter read tool with annotations and an output schema, the description covers matching behavior, scope limits, clarification flow, and empty-result guidance. The only meaningful gap is that no guidance is given on when to escalate to a different sibling tool.

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%, so the baseline is 3; the description earns an extra point by specifying what a good query looks like (brand + product + volume/count, some English support, unknown English words left unchanged) and by explaining the sku alternative. The limit parameter is left entirely to the schema, which is acceptable given its inline description.

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 names a specific verb and resource ('폴슨(folsn)이 네이버 스마트스토어에서 직접 파는 상품을 ... 찾습니다') and bounds the scope to Folsn's own store, explicitly stating it does not return other stores' prices or market-wide lowest prices — which is precisely what separates it from catalog/offer siblings. An agent can tell it apart from search_catalog_products without opening either schema.

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 gives clear positive guidance on how to query (Korean brand + product + volume/count works best, some English names supported) and negative scope (no other stores' prices, no market-wide lowest). It does not name a sibling to switch to when the scope is wrong, so the agent must infer routing from the sibling list rather than being told directly.

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.

Resources