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

Substantially exceeds the annotation set: it discloses internal lookback warming (fetches extra history before start so MA60/MACD are warm, but only returns [start, end]), the MACD histogram convention 柱=2×(DIF−DEA), KDJ 3/3 recursive smoothing seeded at 50, a 5-code batch cap, and the keyless Tencent source. These are operational facts an agent could not derive from readOnlyHint/idempotentHint alone.

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?

Front-loaded with what the tool is and which four indicator families it computes, then builds out mechanics. It is dense and somewhat run-on in the middle section, but nearly every clause (conventions, lookback, code cap, source) carries actionable information rather than 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?

For a 14-parameter tool with no output schema, the description covers the return range and warming behavior, batch limits, and numeric conventions. It stops short of describing the return record shape (e.g., how indicator columns are keyed), which is the one omission for a tool with no output 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?

Schema coverage is 100%, so the per-parameter defaults are already documented and the baseline is 3. The description still adds meaning the schema lacks: the start/end semantics (extra history auto-fetched before start, only [start, end] returned) and the code-limit/ETF-parity behavior, which clarify how to shape a call.

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 (computes MA/BOLL/MACD/KDJ technical indicators for Chinese A-share stocks and ETFs) and explicitly anchors itself against the sibling it overlaps with ('same source and codes as ashares_daily_history'). An agent can distinguish it from ashares_daily_history without opening either schema.

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?

Gives concrete trigger examples ('515050通信ETF华夏最近20个交易日MA5/MA10/MA20', 'MACD是否死叉') and signals selection pressure with 'indicator math is heavier than a plain OHLCV pull', which implies using ashares_daily_history for raw prices. However, it never states that exclusion explicitly, so the when-not is inferred rather than declared.

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