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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds the exact formula and required columns, which is useful behavioral context. However, it does not disclose edge cases, error conditions, or the exact output format beyond returning a DataFrame, which is a gap.

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 verbose and repetitive, with the formula presented in both Chinese and English comments, plus external links and a paper reference. This adds noise and reduces readability. The essential information could be conveyed in two or three concise sentences, making the current length unjustified.

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 includes the formula, input requirements, and return type, but it does not specify the output column name, how to pass data in the JSON format expected by the schema, or how missing/invalid data is handled. The formula itself contains a minor discrepancy (di listed as either ln(Li/Oi) or Li/Oi) that could confuse the agent. With no output schema, these omissions make the description incomplete.

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 has zero descriptions for the 'data' parameter, and the description only says it should be a pandas.DataFrame with OHLC columns. The schema expects an array or object, but the description does not explain this mismatch or how to structure the data as JSON. It lists required columns, providing some value, but fails to bridge the DataFrame-to-JSON gap.

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 calculating Yang-Zhang Realized Volatility from OHLC data, with a specific verb ('计算') and resource. It includes the full formula and differentiates from sibling tools that fetch data rather than compute. The title and description align, making the purpose unambiguous.

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 usage as a calculation tool that requires OHLC data, but it does not explicitly state when to use this tool versus alternatives like rv_from_futures_zh_minute_sina or rv_from_stock_zh_a_hist_min_em. It provides no when-to-use or when-not-to-use guidance, so the agent must infer based on context.

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