価格トライアングル・アービトラージスキャン

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

Annotations declare readOnlyHint=true, destructiveHint=false, openWorldHint=false. The description adds meaningful behavioral context: it cross-checks three data sources, can optionally fetch live transactions (requires API key), and produces different output modes. No contradictions 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 two short paragraphs (English and Japanese) that front-load the core purpose. Every sentence adds value, though the bilingual repetition is slightly redundant. Could be slightly more concise by combining languages, but still efficient.

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 adequately covers input parameters and tool purpose, but does not describe the output schema despite context signals indicating one exists. For a complex analysis tool, explaining the return structure (e.g., a list of cities with scores) would improve completeness. The 'output_mode' parameter partially addresses output format, but not the underlying data.

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 coverage is 100% and each parameter has a description. The tool description adds value by explaining the signal type enum (discount, inheritance_edge, overheated, fair) and the output_mode options (compact vs detailed), which goes beyond the schema's basic property descriptions.

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 identifies the tool as a price triangulation arbitrage scanner, specifying the three price sources (rosenka, koji, tx) and the three signal types (discount, inheritance_edge, overheated). This distinguishes it from sibling tools like 'assess_property_risk' or 'forecast_land_price_trend'.

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 states what the tool does but does not explicitly guide when to use it versus alternatives. Given 36 sibling tools, lacking 'when not to use' or references to related tools (e.g., 'composite_value_score') reduces effectiveness for an AI agent deciding between tools.

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