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

With no annotations, the description carries the full burden and does: it discloses hard caps (专业版 200 / 机构版 300), per-returned-item billing, a paid-tier prerequisite (¥99 专业版+, 标准版 unavailable), unsupported markets returning ok:false, and measured latency versus looping the single-code endpoint. It also discloses the exact return shape (data[{code, ok, data|error}] + requested/returned/failed), which is behavioral information beyond the request itself.

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?

Purpose is front-loaded and the alternative/limits follow in a usable order, but the ⚠️ blocks are dense and partly redundant — the 200/300 cap appears both in the prose and in the codes schema, and the 'why this deserves its own call' performance paragraph, while useful, is longer than it needs to be. Efficient in content, slightly noisy in form.

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 one-param batch endpoint with a mandatory paid tier and market-specific section semantics, the description covers everything an agent needs to call it correctly: input format, caps, billing, unsupported markets, per-item failure handling, and the critical warning to index results by market/slug rather than ordinal. An output schema exists, yet the description still supplies the cross-market semantic caveat the schema cannot express.

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% and the single param is already documented with format and caps, so baseline is 3; the description adds meaning beyond the schema by noting that bare 6-digit codes are accepted and that HK codes (hk00700) can be mixed into the same comma-separated list. That mixed-market input rule is the kind of detail an agent would otherwise get wrong.

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 first line states a specific verb and resource ('批量股东研究：一次拿多只的十大股东 / 十大流通股东 / 股东户数统计') plus the differentiator (逐只标明成功与否). It also names the sibling it replaces (ashare_shareholder) and what that sibling does differently, so an agent can route without opening any 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 gives explicit trigger phrasings ('这几只谁在持有/股东户数变少了吗/股权集中不集中/机构在不在里面'), states the alternative and the condition that selects it (multi-code with per-code status ⇒ use this; single-code also acceptable here), and warns when not to use it (北交所/ETF/指数/美股). Almost nothing is left to inference.

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