経路検索（Yahoo!乗換案内）

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

With no annotations, the description carries the burden of behavioral disclosure. It does state the output data (time, duration, fare, transfers, routes), and explains the mode parameter's effect. However, it does not explicitly confirm the operation is read-only (though '検索' implies it), nor does it describe error handling, whether multiple route options are returned, or pagination. These omissions leave some behavioral aspects unclear, but the core behavior is adequately conveyed.

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 two concise sentences, front-loaded with the core action and output summary. Every sentence contributes essential information: the first describes purpose and return data, the second clarifies mode usage. There is no redundancy or filler.

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 12 parameters and no output schema, the description provides a strong foundation by listing the key return fields and special mode options. It does not mention the boolean filters (useExpress, useAirplane, etc.) or sorting variants, but these are well-described in the schema. For an agent to correctly invoke the tool, the combination of schema and description is sufficient, though more context on default behavior (e.g., current time defaults) would round it out.

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?

The input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds little beyond this, except a natural-language restatement of the mode parameter's special values (first/last train). No additional parameter meanings or format details are introduced, so it neither improves nor degrades the schema information.

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 explicitly states '出発地から目的地までの電車経路を検索する' (search train routes from departure to destination), a specific verb and resource. It further distinguishes itself from siblings by detailing the outputs: '時刻・所要時間・運賃・乗換回数・各区間の路線と番線を返す' (returns time, duration, fare, transfers, route and platform), clearly separating it from station search or timetable tools.

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 clearly defines the tool's context (route search between two points) and adds specific guidance for special modes: '終電は mode=last_train、始発は mode=first_train' (last train via mode=last_train, first train via mode=first_train). However, it does not explicitly name alternative tools or exclusion criteria, so it falls short of a 5. The context is clear enough for an agent to know when to select it.

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