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

No annotations provided, so the description carries full burden. It correctly identifies this as '只读查询' (read-only query), which is critical behavioral information. It also warns that historical modes require a real trading day and return empty on non-trading days ('非交易日返空'). It could go further on rate limits or response shape, but the read-only nature and the trading-day constraint are the key operational facts.

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 description is dense but front-loaded: it leads with the core concept and usage scenario, then enumerates modes, then lists fields. Every sentence serves a purpose, though the field enumeration (reason, pct, board_desc, etc.) is somewhat lengthy and could arguably be inferred from the output schema. Still, the structure is logical and information-rich.

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?

With an output schema present, the description need not explain return values in detail, yet it does list key fields, which is helpful but redundant. The description covers all three parameters' semantics, the read-only behavior, the trading-day constraint for historical modes, and the mode selection logic. The only gap is lack of explicit mention of rate limits or pagination, but for a read-only query with a limit parameter, this is minor.

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 schema already documents each parameter and mode value. The description restates the mode enum values but adds little new semantic depth—the same information is in the schema's mode description. The date format and limit constraint appear in both places. The description does add the '历史类 mode 的 date 须为真实交易日' warning, which enriches the date parameter meaning beyond the schema.

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 opens with a specific verb+resource pairing: '异动/偏离值（短线监管异动体系）' and immediately identifies it as the short-term regulatory anomaly detection system. It goes further to enumerate multiple sub-modes (严重异动, 10日100%偏离, 盯盘名单) that tell an agent precisely what data surface this tool covers. This clearly distinguishes it from siblings like ashare_changedist or ashare_lhb.

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?

Explicitly states when to use: '用户问今天有哪些异动股/偏离值/触发严重异动/被监控的票/短线风险股用这个.' It then maps each mode to its use case (deviation for today's hot list, deviation_hist needs date, abnormal needs date, watch for today, alert for severe anomaly alerts). The condition for each mode is fully spelled out.

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