ETF 调仓拥挤度预警

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

With no annotations provided, the description carries the full burden, and it delivers: it discloses the scoring formula (共同率权重、平均权重集中度、被持有 ETF 数量), the semantic interpretation (共同率越高 = 抱团越紧 = 潜在踩踏/反转风险越大), and the output shape (拥挤度分档 低/中/高 + 预警提示). It does not cover data-source freshness, fetch behavior, or empty-result edge cases, but for a read-only analysis tool the core behavioral semantics are well disclosed.

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 single paragraph contains no fluff — every sentence carries signal (basis, function, risk interpretation, scoring components, output format) and the core action is front-loaded in the first clause. It could be slightly better structured with explicit labeling of inputs vs. outputs, but it is dense and economic.

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?

There is no output schema and no annotations, so the description must explain return values; it does state the return format (分档 低/中/高 与预警提示) and the full decision logic behind it. For a moderately complex 2-parameter tool this is largely complete, though an example alert or a note on data dependency (what happens if the provided ETFs share no holdings) would close the remaining gap.

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 100%, so the baseline is 3: the schema already documents etf_codes (comma-separated ETF codes with example) and top_n (number of targets, default 15). The description adds marginal meaning by stating the analysis targets 共同率最高的标的, which clarifies that top_n selects the most crowded targets, but it does not compensate beyond that.

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 resource (同 ETF 共同持仓核心标的), a specific verb (输出拥挤度评分与反转预警), and defines its scope (共同率最高的标的). The analytic function — crowding scoring plus reversal alerting — is clearly distinct from data-retrieval siblings like etf_core_holdings or fund_holdings, but it never names a sibling or explicitly states what it is not, so it falls short of full 5 differentiation.

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?

Usage context is implied rather than stated: by describing crowding-score computation and risk interpretation, the description signals it is for institutional-clustering/reversal-risk assessment on same-theme ETFs. However, there is no explicit when-to-use statement, no when-not-to-use guidance, and no named alternatives (e.g., etf_core_holdings for raw holdings lists), leaving the agent to infer routing.

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