夏普·索提诺

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

Annotations declare readOnlyHint=true and openWorldHint=true. Beyond that, the description discloses the derivation path ('拉取 K 线推导收益率'), what is computed ('年化收益/波动、夏普与索提诺'), and the auto-inference behavior of periodPerYear. It also discloses the limitation that small windows have limited statistical meaning, which is honest and useful. This is more than annotations provide.

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 compact and information-dense: three sentences, each contributing a distinct semantic block (what it computes, what it measures, how periodPerYear is defaulted, and a usage caveat). It is well-structured for an AI consumer.

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 explains the core behavior, the derivation approach, the parameter defaulting strategy, and a statistical caution. It doesn't describe the return value shape beyond an available output schema, so the output_schema likely covers that. Missing details such as how to treat riskFreeRate defaults or exact timezone conventions are minor against the available annotations and schema.

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's description coverage is about 40% (only periodPerYear and riskFreeRate have descriptions). The description adds meaning by explaining the default behavior of periodPerYear (auto-inferred by interval) and the meaning of riskFreeRate remains opaque, but the description doesn't detail all five parameters. It adds semantics for the timing, but not the format of symbol, limit, or riskFreeRate; the schema already provides some parameter domains. The description partially compensates for the schema gaps.

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 specific verb ('拉取 K 线推导标的收益率序列') and resource ('标的收益率'), and explicitly scopes the metric to '标的价格序列的风险特征（非账户绩效）', distinguishing it from account-focused tools. However, it doesn't name a specific sibling alternative, so differentiation from other analysis/indicator siblings is implicit rather than explicit.

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 clearly scopes the tool to '标的收益率序列' and explicitly excludes '账户绩效', noting that 'serious evaluation' should use larger windows. However, it doesn't explicitly describe when to use this tool instead of other indicators/analysis tools, leaving some inference to the agent.

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