RSI 背离检测

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds meaningful behavioral detail beyond that: it internally pulls K-lines ('拉取 K线后检测') and explains the half-window extreme-comparison algorithm, so the agent knows the tool has internal data dependencies and what computation drives the result. No contradiction with the read-only annotations.

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 compact Chinese sentence conveys purpose, pipeline (K-line fetch --> detect), and return concept (divergence type + extreme details) with little waste. A very small deduction for the '直连版' prefix, which may confuse agents by hinting at a nonexistent sibling version.

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 tool has 5 parameters, covers output schema, and a read-only annotation, the description covers the core 'what' and 'algorithm' but not edge behavior (e.g., what happens when there is insufficient data, how many divergence results are returned, or the relation between lookback/limit/rsiPeriod. An agent can call it correctly with schema-provided defaults, but may be surprised by edge-case results.

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% (only lookback is explained), so the description should compensate. It partially does: '前后半窗极值对比' gives context for lookback's window semantics. But rsiPeriod, limit, symbol, interval and their interplay are not elaborated in either the schema or the description, and defaults (14/200/20) are standard enough that agents are likely to call correctly without further detail.

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?

States a specific verb+resource: it detects price-vs-RSI top/bottom divergence ('检测价格与 RSI 的顶背离 / 底背离'). The '前後半窗极值对比' mechanism makes the function concrete, and divergence is a unique concept among the indicator siblings, distinguishing it from indicator_rsi, indicator_macd, etc. It loses a point only because it never explicitly names an alternative or a differentiation against the other indicator tools.

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 intended use — проверка divergence between price and RSI — is clear, so when an agent needs divergence detectentation this tool is the obvious choice. But there is no guidance on when NOT to use it, no mention of raw-als indicators like indicator_rsi for plain RSI values, and no statement about alert-window tuning. Usage is implied rather than stated.

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