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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds valuable context beyond this: the prefecture-level matching (station master is Greater Tokyo), the fact that it's a 'Relay of official JMA facts' (not original analysis), and that it excludes general warnings. These traits meaningfully shape agent expectations.

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, each earning its place: what it is, how to query, and scope/caveat. The dash for exclusion is efficient. No padding.

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?

For a one-parameter tool with an output schema, the description covers content type, query language, matching scope, and source. It gives the agent enough to decide when to use it and what to expect, without needing to inspect the 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 100%, and the description reinforces the Japanese/romaji format. It also adds the nuance that the station_name is used for a prefecture-level match, which is extra meaning beyond the schema's simple 'station name' definition. This justifies a score above the baseline 3.

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 states the tool provides 'Live JMA river flood forecasts and landslide alerts affecting a station's prefecture' and explicitly excludes 'general weather warnings', distinguishing it from likely siblings like get_active_alerts. The verb 'Live' and resource 'JMA alerts' are specific and unambiguous.

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 gives clear usage context: ask by station name in Japanese or romaji, and notes the prefecture-level match. It explicitly says 'NOT general weather warnings', which provides a when-not scenario. However, it does not name alternative tools directly, so it falls short of full 5.

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