VaR · CVaR

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

在注解已有 liveHint=true 与 openWorldHint=true 的基础上，描述补充分传了额外行为：历史模拟法、计算对象为收益率序列、单一 K 线对象的含义，以及重要符号约定'负值=损失'。这些信息能防止把结果直接读作另一层含义，帮助智能体正确理解调用后的结果。

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?

全部内容只有两条有效句子：第一句讲计算对象、方法、结果并通过符号约定；第二句给出阈值且是真正可执行的止损指导。每句都有独立价值，无冗余，起点句在句首，结构紧凑清晰。

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?

在已有输出 schema 以及 readonly/openWorld 注解的前提下，描述已覆盖计算全员向量、统计方法、置信度、结果定义容忍、适用配置六个关键，能让智能体有安全决策所需的信息。只差少量有关结果输出格式与极端置信度（limit 过小）注意事项的更多补充，不给失去完整分。

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 文本覆盖率仅 25%（只有 confidence 有描述），需要描述补齐参数含义。描述通过'K线——收益率——VaR/CVaR'的链路让 symbol 与 interval 的实际角色自然成立，也暗示了 limit 的效率与样本采样意义。虽然没有逐参数列名说明，但已能给充分弥补了 schema 的缺口。

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?

描述正确定义了动词与资源：拉取 K 线推导收益率，按历史模拟法计算置信度下的 VaR 与 CVaR。通过'度量工具后单根 K 线尾部风险，非账户绩效'进一步将它与 analysis_sharpe、analysis_drawdown 等账户/策略类评估分开，属于清晰的用途定义。

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?

明确说明了该工具的核心情境——单根 K 线尾部风险——并提出了参考规则：止损 ≥ 单根 VaR × 杠杆，否则可能被正常波动扫损。'非账户绩效'是对应用范围的明确排除，可视为一种边界说明；缺点是没有直接指出应与哪个具体兄弟工具对比使用中选择。

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