compare_close_vs_vwap

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

Annotations declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds valuable behavioral context beyond these: the formula VWAP=Va/Vo (None when Vo=0), the interpretation of close vs VWAP, data availability timing, and cache-only behavior (no API call). This extra context significantly helps the agent understand what the tool does and its data nuances. 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 well-organized and front-loaded, starting with the primary purpose. It then provides usage guidance, formula, data timing, plan support, and an argument list. Every sentence adds unique value, and the structure makes it easy to scan. Despite having several sections, it remains appropriately concise without redundancy.

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 single-stock VWAP comparison tool, the description covers purpose, scope, usage, interpretation, formula, data timing, supported plans, cache behavior, and all parameters. An output schema is indicated as present, so the description need not explain return values. The context is complete for an agent to correctly select and invoke the tool.

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 carries the full burden. It thoroughly explains every parameter: 'code' as required stock code, 'date' as a single date that overrides the range, and 'date_from'/'date_to' as an inclusive range. It also provides accepted date formats (YYYYMMDD or YYYY-MM-DD). This fully compensates for the missing schema 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 states the tool's function with a specific verb ('Compare'), resource ('a stock's close to its daily VWAP'), and scope ('for one code'). It explicitly distinguishes from cross-sectional screeners, making it easy to differentiate from siblings. The additional explanation of buying/selling pressure reinforces the purpose.

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 explicit usage context: 'Use for VWAP・買い圧力・売り圧力 queries on a specific stock; not a cross-sectional screener.' It clearly states when to use and when not to, and also includes data availability timing (~17:15 JST on trading days). No alternative tool is named, but the 'when-not' clause is sufficient for effective selection.

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