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

With no annotations, the description carries the full behavioral burden and does a good job by specifying what data the tool exposes: an 81-city list sorted by cheapest price, monthly national medians, and per-city history. It does not describe output shape, update frequency, or access constraints, so it falls short of a 5.

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 information-dense: purpose, data contents, parameter guidance, and sibling routing are each covered without filler. The core scope ('1つの品目') is front-loaded, and the cost_index pointer is placed at the end where it can redirect without obscuring the main purpose.

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 lookup with no output schema and no annotations, the description is largely sufficient: it names the data views, gives code examples, and routes list requests to a sibling. It could be more complete by describing the return format or date coverage, which is why it is not a 5.

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 schema already documents 'code' as 品目コード4桁 with 100% coverage, so the baseline is 3. The description adds value by giving real examples (1303, 3001, 7301) and making the mapping from code to item explicit, though it does not enumerate all valid codes.

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 opens with '1つの品目の都市別の調査価格', clearly identifying the resource and scope: survey prices for one item across cities. It then enumerates the specific data views returned — the latest 81-city list, monthly national median, and per-city history — and ends with '一覧は cost_index で', which distinguishes it from the sibling list tool.

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 the appropriate usage context clear: use this for single-item city price detail, national medians, and history, and explicitly sends list-ranking requests to cost_index. Concrete code examples (牛乳 1303, 民営家賃 3001, ガソリン 7301) further guide invocation.

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