도시별 단기 날씨 예보를 조회합니다.
Args:
city: 도시 이름 (예: "서울", "부산", "제주", "수원"). 25개 주요 도시 지원.
hours_ahead: 앞으로 몇 시간 예보를 볼지 (기본 24시간, 최대 72시간)
Returns:
시간대별 기온, 강수확률, 하늘상태 등 날씨 정보
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes | ||
| hours_ahead | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It discloses that this is a read-only query ('조회합니다'), supports 25 major cities, limits forecast range to 72 hours, and describes the return contents. It does not cover edge-case behavior such as unsupported city handling or units, but it is reasonably transparent for a simple forecast tool.
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?
The description is compact and well-organized. The purpose is stated up front, and the Args/Returns format makes parameter semantics easy to scan. No unnecessary elaboration or repetition.
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?
Given an output schema exists, the description does not need to fully restate return details. It covers required input semantics, supported cities, and limits. A slight gap is that the full list of 25 supported cities is not provided, but the examples and sibling 'list_supported_options' make this manageable.
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 0%, so the description must explain the parameters itself. It does so well: 'city' gets example values and supported-city scope, and 'hours_ahead' gets a default of 24 and an explicit maximum of 72. This adds real meaning beyond the schema.
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?
The description clearly identifies the resource (short-term weather forecast), the action (lookup/query), and the scope (city-based). It is specific enough to distinguish from siblings like get_air_quality and get_real_estate_trades.
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?
The description makes its intended use clear: retrieving short-term weather forecasts for supported Korean cities. It does not explicitly mention alternatives or when not to use it, but the sibling tools are distinct enough that the context is clear.
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.