get_weather_forecast

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

With no annotations present, the description carries the full burden of behavioral disclosure. It discloses the temporal window (36 hours) and data types covered, but doesn't mention that this is a non-mutating read operation, potential error conditions (e.g., invalid county), or rate limits—leaving an incomplete safety picture.

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?

Two sentences with zero waste. The core purpose is front-loaded first, followed by a single essential parameter constraint. Every sentence earns its place.

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?

The output schema covers return values, so that burden is lifted. The single parameter is well-documented with format guidance and an example. Remaining gaps—no error behavior or explicit read-only confirmation—are minor given the tool's simplicity and existing output schema.

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% and the schema only labels the parameter as 'County' with no description, so the description must compensate. It does so effectively by specifying the exact format (must be a full county name from cwa://counties) and providing a concrete example (「臺北市」), which is valuable 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 states a clear verb-initial function (查詢不明確未來36小時天氣預報) with specific outputs (天氣現象、降雨機率、氣溫). The scope is well-defined and distinct from siblings which cover earthquakes, warnings, and typhoons, although it doesn't explicitly name them.

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?

It clearly specifies the usage condition (querying forecast for a specific county) and imposes the county format requirement. However, it doesn't give when-not-to-use guidance or explicitly contrast with sibling tools, leaving the alternative-selection to the agent's inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.