cheapest_by_data데이터 1·5·10·15·30·70·100GB 이상 구간마다 지금 가장 싼 평생 할인·정가 요금제와 기간 할인 요금제(할인 종료 후 요금·24개월 총액)를 비교합니다. "알뜰폰 최저가·추천" 질문에 먼저 쓰세요. 통신망·5G·통화 무제한·소진 후 속도·유심 무료로 좁힐 수 있습니다.
| Name | Required | Description | Default |
|---|---|---|---|
| mno | No | 빌려 쓰는 통신망 | |
| qosMin | No | 데이터 다 쓴 뒤 최소 속도 kbps (예: 1000=1Mbps, 3000=3Mbps, 5000=5Mbps) | |
| network | No | ||
| usimFree | No | 요금제에 "유심 무료"가 공식 원문으로 적힌 요금제만 | |
| voiceUnlimited | No | 통화 무제한만 |
Changes observed during successful MCP inspections.
Input schema / properties / qosMin / descriptionPrevious value: -"데이터 다 쓴 뒤 최소 속도 kbps (예: 1000=1Mbps, 5000=5Mbps)"New value: +"데이터 다 쓴 뒤 최소 속도 kbps (예: 1000=1Mbps, 3000=3Mbps, 5000=5Mbps)"Input schema / properties / usimFreeAdded value: +{
+ "description": "요금제에 \"유심 무료\"가 공식 원문으로 적힌 요금제만",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is low; the description usefully adds what is actually compared (post-discount price, 24-month total) for each plan type. It omits default behavior when no filters are supplied (0 required params), which is the main undisclosed trait.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with the core comparison, then usage, then filters. Dense and Korean-idiomatic with no filler, though the tier enumeration is slightly list-heavy for the payload it carries.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description must carry return-value burden; it names two metrics (post-discount price, 24-month total) but not the result shape, tier-by-tier grouping, or behavior with zero filters. Adequate for invocation, incomplete for predicting output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 80% and already documents most fields, but the description maps all five filters to plain-language dimensions (network carrier, 5G, unlimited voice, post-exhaustion speed, free USIM), reinforcing how each narrows results. It adds interpretation rather than syntax, so it stays above the baseline-3 floor.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a concrete verb (비교합니다) and resource (평생 할인·정가 요금제 vs 기간 할인 요금제) scoped to explicit data tiers (1/5/10/15/30/70/100GB). An agent can tell what it produces, though it never names a sibling tool like search_plans or price_index to draw the boundary explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"알뜰폰 최저가·추천" 질문에 먼저 쓰세요 gives a clear first-choice condition, and the filter list (통신망·5G·통화 무제한·소진 후 속도·유심 무료) shows how to narrow. No when-not condition or named alternative is given, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.