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

No annotations are provided, so the description carries the full burden and does so well: it discloses that no weights are returned, that it is a static profile cached for 1 hour, that it requires the ¥29.9+ paid tier, that only one index per call is accepted (comma-separated returns empty), and that output key names differ by market. These are exactly the behavioral traits an agent would otherwise get wrong.

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 core scope and the alternative-tool routing are front-loaded, which is good, but the repeated ⚠️ blocks are verbose and partially redundant (ashare_etf(kind='持仓') is recommended twice; weights are disclaimed twice). The density of warnings is defensible for the failure modes it prevents, but it could be tightened without losing information.

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 single-parameter lookup with an output schema, this covers everything an agent needs: what it returns, what it does not return, how to get the missing piece, which inputs are valid, and the per-market field-name divergence that would otherwise break downstream parsing. Nothing material is missing.

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% with examples already in the schema, so baseline is 3; the description adds real constraint semantics on top — accepted code formats (sh000xxx / sz399xxx / hk*), specific HK index codes, and the single-code-only rule. Minor gap: it does not restate the default or say what happens on an unknown code.

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 concrete verb+resource (full constituent list of an index) and enumerates the supported indices (沪深300/上证50/中证500/科创50/恒生...). It also explicitly distinguishes itself from the nearest sibling, ashare_etf, on both the weight dimension and the ETF-basket dimension.

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?

Names the triggering user questions ('沪深300有哪些成分股/ETF底层持有什么'), states when to use the alternative (weights → ashare_etf(kind='持仓'), top20Ratio), and states exclusions (individual stocks/ETFs → ashare_etf; ETF PCG lists are a different tool). Exclusions and alternatives are both explicit.

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