地価トレンド予測

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds behavioral specifics: the forecasting methods (linear regression, moving average), return values (CAGR, confidence interval, investment signal), and a coverage constraint (10 prefectures). This provides useful context beyond the annotations without contradiction.

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 in English with a Japanese translation, front-loaded with the core purpose. Every element (method, outputs, coverage) is necessary and informative, with no redundant or vague phrasing.

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 the tool has 7 parameters and an output schema, the description covers the core functionality and outputs well. However, it does not explain the '10 prefectures' limitation or mention the 'output_mode' and 'includeMarkdown' parameters, which are configurable. The output schema likely addresses return values, so the description is mostly complete but could be more explicit about constraints.

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 86%, so the schema already documents most parameters. The description mentions methods (linear regression, moving average) corresponding to the 'method' parameter and alludes to outputs, but does not detail parameters like 'city', 'horizon', or 'landUse'. Thus, the description adds limited parameter-specific value beyond the schema.

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's purpose: 'Forecast land price trends using linear regression and moving average.' It specifies the outputs (CAGR, confidence interval, investment signal) and mentions coverage (10 prefectures). The verb 'forecast' and resource 'land price trends' are specific, and the description distinguishes this tool from siblings like 'assess_property_risk' or 'portfolio_optimizer' by its focus on price trend prediction.

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 implies the tool is for land price forecasting but does not provide explicit guidance on when to use it versus alternatives (e.g., 'scenario_what_if' or 'predict_corporate_demand'). No when-not-to-use instructions or exclusions are given, though the context of price trend analysis is clear.

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