診療報酬・薬価検索

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

With no annotations provided, the description must carry the behavioral disclosure burden. It discloses two relevant behaviors: it works offline (no network) and it attaches the included file name to results to indicate version due to fee revisions. It does not mention error handling, pagination, or the prerequisite that the master must be imported, though the latter is implied. Given the absence of annotations, a score of 3 is appropriate—it reveals some key traits but leaves gaps.

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 three short Japanese sentences, each contributing a distinct fact: purpose, offline availability, and result metadata. It is front-loaded with the core purpose and does not contain fluff. It could be slightly more structured (e.g., listing parameters), but it is appropriately concise for its length.

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 description leaves out essential context for correct invocation. It does not explain what each 'kind' value means, which is critical for selecting the right search scope. It also doesn't clarify that data must be imported first (though '取り込み済み' implies it) and doesn't reference the sibling shinryo_master_status for checking readiness. The output schema exists, so return value structure is likely covered, but the missing parameter semantics and prerequisite context make this incomplete for an agent.

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 description coverage is 0%, so the description must compensate. It explains that the 'term' parameter can be a name, kana, or code, which adds value. However, it does not explain the 'kind' parameter (shinryo, iyakuhin, tokutei) or the 'limit' parameter beyond their schema defaults. The enum values are left undefined, and no examples are given, leaving the agent to infer their meaning. Partial coverage only, hence a low score.

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 verb 'search' and the resource 'ingested medical fee master', and specifies search criteria (name, kana, code). It also notes offline operation, which helps differentiate it from network-dependent search alternatives like search_drug. However, it doesn't explicitly name sibling tools or clarify that it covers both medical fees and drug prices (though the title implies this), so it stops short of a perfect 5.

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 provides no explicit when-to-use or when-not-to-use guidance. It mentions offline capability and that results include a file name, but does not indicate when to prefer this over sibling tools like search_drug or fetch_drug_entry. The context that data must be ingested is only implicit via '取り込み済み' (ingested).

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