随机指标 KDJ

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

Annotations already mark it readOnly and openWorld, and the description adds that it computes from pulled K-line data and returns a K/D/J sequence. It does not cover failures or odd-specific shape, but the readOnly annotation reduces the need for mutation/risk disclosure.

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?

A single, front-loaded sentence that states the input action, the output format, and the tunable parameters with minimal filler.

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?

Given the output schema and read-only annotations exist, the definition is almost sufficient for simple invocation. However, the kSmoothing/kSlowing mismatch and lack of usage context leave a meaningful gap in advisory quality.

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 description tries to add parameter meaning by listing kPeriod/kSmoothing/dPeriod as adjustable, but the schema only contains kSlowing, not kSmoothing, so an agent could generate an invalid parameter. Since schema description coverage is 0% and limit/symbol/interval meanings are left unstated, the description does not fully compensate for the schema 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?

Description clearly states it pulls candlesticks and computes a KDJ stochastic indicator, returning a K/D/J triple series. This specific output distinguishes it from generic 'indicator_*' siblings.

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?

No guidance is given on when to choose KDJ versus the many sibling indicator tools, and no exclusions or alternative conditions are stated. '直连版' hints at a variant but does not explain when to use it.

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