企業需要予測

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds context about sectors and geographic scope but does not elaborate on rate limits, authentication, or other behavioral traits. No contradiction with annotations.

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 extremely concise: two short sentences covering purpose and scope. Front-loaded with the verb. No superfluous words.

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 covers the main purpose and sectors, but lacks specificity about which prefectures are included and does not mention the output format even though an output schema exists. Leaves some ambiguity about geographic scope.

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?

Input schema has 80% description coverage, so baseline is 3. The tool description does not add any additional meaning or usage context for the parameters. Parameters like 'neighborhood' have schema descriptions but the tool description does not explain how they affect the prediction.

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 it predicts corporate demand scores for manufacturing, office, and retail across 10 prefectures. However, the input schema includes property types like logistics and commercial not mentioned, causing slight inconsistency. It distinguishes from sibling tools like assess_family_friendly_score by focusing on corporate demand.

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?

No guidance on when to use this tool versus alternatives. The sibling tools list is provided but no explicit context about when to choose predict_corporate_demand over tools like scenario_what_if or portfolio_optimizer.

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