波动率状态分类

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

Annotations already provide readOnlyHint=true and openWorldHint=true, so the description only needs to supplement actual behavior. It adds the algorithm source (Bollinger bandwidth percentile) and output categories, which give useful transparency. It still omits minor behavioral details such as what happens with insufficient data or whether the output is a series or single-of-state, though output schema metrics may cover some of this.

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 a compact one-liner that carries the formula, categories, and intended purpose without redundant wording. The qualifier '直连版' is slightly unexplained but does not bloat the sentence. It is near-ideal in size and accessibility.

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?

An output schema exists, so the return-value description is not strictly needed. The formula, output states, and position-management purpose give the core context, but the absence of sibling-tool routing and full parameter population left the agent somewhat limited when disambiguating this tool, from Bandwidth and ATR or setting the right limit.

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 only 20% since only, lookback has a schema description. The description indirectly connotes meaning for bbPeriod and lookback via '布林带宽百分位', but it does not expressly name or explain all parameters like limit, symbol, or interval. It partially compensates for the missing schema documentation, so semantics are clearer than a bare param-list but still incomplete.

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 states a clear verb-based role: it classifies volatility regimes from Bollinger bandwidth percentile and enumerates the five output states (squeeze, low_volatility, normal, high_volatility, expansion). This makes the tool functional-purpose obvious, though it does not explicitly contrast with sibling volatility indicators such as bbands or ATR.

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 phrase '辅助仓位管理' provides a plausible use context (position sizing decisions). However, it does not say when to choose this over alternations like indicator_bbands or indicator_atr, nor defines exclusion conditions or setup prerequisites. The use case is inferred, not explicitly routed.

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