Skip to main content
Glama

Cigo Aircare & Carsafe

Search Carsafe

search_carsafe
Read-only

Find Cigo Carsafe cabin air / pollen / car AC replacement filters by vehicle model, generation code and model year, including Korean and supported English names (e.g. Hyundai Santa Fe TM, Kia Sorento). Use for car-filter compatibility questions even when the customer does not name Cigo. Returns Korean-market reference fitment, dimensions and both Cigo own-store and Naver domestic purchase links. Show both available options; prefer the own-store link when the customer asks to buy. Links do not create accounts, carts, orders or payments. Do not claim a purchase is complete. Not a comparison of all brands. Ask for year/generation when ambiguous. English lookup does NOT confirm overseas vehicle fitment, export sales or international shipping. Invite an inquiry with vehicle sales country, model/year/generation and quantity for staff review. 차종·세대·연식별 차량용 에어컨/캐빈 필터 호환 규격과 국내 구매 경로 조회. 해외 사양 호환·공급·배송은 담당자 확인을 위한 문의로 안내합니다.When showing product imagery, use only the returned image_url and image_alt. Render it as a Markdown image if supported, otherwise provide the image link. Do not use image search, image carousels, stock photos or generated substitutes for these products. If inline display is unavailable, show the exact official image link instead of another image. Keep image_caption visible. Do not invent image URLs or treat representative photos as exact model evidence. Product lookups record channel labels and returned product codes for Cigo's usage analytics. Reuse the returned journey_token only within this customer's current conversation when calling another product lookup or submit_b2b_inquiry. Never invent a token or reuse one for a different customer. If unavailable, omit it. Do not display the token in sales replies.

Input Schema

NameRequiredDescriptionDefault
yearNo
model_nameYes
journey_tokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / journey_token
      Added value: +{
      +  "default": "",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), yet the description adds the actual return payload (Korean-market reference fitment, dimensions, own-store and Naver domestic links), states that links create no accounts/carts/orders/payments, and discloses that channel labels and product codes are logged for analytics. The journey_token lifecycle rules and the Korean-market-only limitation are behavioral facts found nowhere in structured data.

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?

Correctly front-loads purpose and usage in the opening sentences, but then sprawls into image rendering policy, analytics disclosure, token handling and sales-reply guardrails in one undifferentiated block. Much of that content governs agent reply behavior rather than tool selection, so the definition is longer than the selection decision requires even though individual sentences are not empty.

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 supplies the return shape (fitment, dimensions, two purchase links) and the constraints an agent needs before calling: year/generation ambiguity, Korean-market-only reference data, non-confirmation of overseas fitment or shipping. It also handles the follow-on path (inquiry with country/model/year/generation/quantity), leaving nothing material unaddressed.

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 description coverage is 0%, so the description must carry parameter meaning, and it largely does: model_name is defined by accepted naming (Korean and English, model plus generation code such as 'TM'), year is flagged as needed when ambiguous, and journey_token gets detailed reuse/omission/non-display rules. The gap is that generation code is repeatedly referenced as an input but is not a distinct parameter, leaving how it maps into model_name implicit.

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?

States a specific verb and resource (find Cigo Carsafe cabin air / pollen / AC replacement filters) plus the exact identifiers accepted (vehicle model, generation code, model year) and naming conventions with concrete examples (Hyundai Santa Fe TM, Kia Sorento). It also explicitly bounds scope ("Not a comparison of all brands"), which separates it from get_hvac_filter_info and the inquiry sibling.

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?

Gives explicit triggers ("Use for car-filter compatibility questions even when the customer does not name Cigo"), an ambiguity rule ("Ask for year/generation when ambiguous"), a preference rule on which link to surface, and a routing rule to staff review via inquiry when overseas fitment/shipping is at stake. It also names the exclusion (not a brand comparison), so the agent can pick the right sibling.

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