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

No annotations exist, yet the description discloses the traits that actually block misuse: only current-day data (most recent trading day on holidays/pre-open, verifiable via top-level `day`), an in-progress point count (~242 points, growing during the session), the aggregation caliber of the metric, and that non-institutional tiers get an explicit message plus upgrade link rather than silent failure. That is exactly the behavioral context annotations would otherwise carry.

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: definition and `net` semantics first, then usage triggers, then caveats, then sibling split. Every caveat carries real information, but the heavy ⚠️/emoji formatting and repeated warnings make it denser than a scanning agent would prefer.

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?

Output schema exists so return values need not be explained, and the description still points to the top-level `day` field an agent must read. Access gating, timing behavior, metric caliber, and the sibling boundary are all covered — nothing needed to call it correctly 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?

Single parameter `code` with 100% schema description coverage (sh600667 or 600667), so the schema already does the work. The description adds no extra syntax, market-prefix, or validation meaning beyond it — baseline 3 for a fully documented single param.

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 resource and granularity — "单股 L2 大单资金分时（分钟级）" — and immediately defines the semantics of the only output concept (`net` = 大单净额，正=净买入). It also names what it is NOT (逐笔委托 / 十档盘口) and separates itself from `ashare_fund`, so an agent can place it without opening schemas.

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 phrasings ("大单在买还是卖/主力资金分时/哪一分钟砸盘") and an explicit split rule against `ashare_fund` (趋势 vs 快照). However it never differentiates among the six closely-named siblings (ashare_bigorder_flow, _history, _queue, _rank, _split), which is the main confusion risk for this tool.

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