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

With no annotations, the description carries the full burden and does well: it discloses that the data source always returns 100 trading days, that limit only truncates locally (saves bandwidth, not calls), that the metric is the big-order caliber and is not 主力净额/龙虎榜/逐笔, and that non-institutional tiers get an upsell message instead of data. It doesn't cover error behavior or response size beyond the fixed 100 rows, which keeps it just short of a 5.

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 returns, then when to use it, then the sibling split, then caveats — a sensible order with essentially no filler. The heavy ⚠️/⭐/⛔ marker formatting is dense but each sentence carries 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?

An output schema exists, yet the description still names the row fields (date/net) and their semantics, which is a bonus rather than a redundancy. Combined with the tier restriction and truncation caveat, an agent has everything needed to call this correctly and to explain the result.

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 baseline is 3, but the description adds real meaning the schema doesn't: limit is a local truncation of the fixed 100-day payload and does not reduce the underlying call. The row field names and unit (元, positive = net buy) are also spelled out.

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 gives a precise verb and resource (L2 历史大单净额, daily, up to 100 trading days back) and states the unit (元) and ordering (倒序). It explicitly distinguishes itself from the sibling ashare_bigorder, so an agent can pick between them 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?

It names the user phrasings that trigger it (吸筹/趋势/前几个月怎么走) and states the alternative explicitly: ashare_bigorder only covers today, while this tool provides the backward look for judging sustained accumulation vs a one-day spike. There are no exclusions an agent must infer.

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