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

With no annotations, the description carries the full burden and does so thoroughly: paid tier requirement (¥99+), per-call caps (200 pro / 1000 institutional), billing by actual returned count (failures not charged), market coverage (A-shares full; HK only main net inflow; US returns ok:false), and a critical warning that ok:true on the array does not guarantee per-stock data. That last point is exactly the kind of behavior an agent cannot infer from schema or annotations.

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 purpose and the sibling distinction, then organized into labeled warnings (usage, return structure, caps, billing, coverage, paywall). It is dense but every section earns its place; the caps and comma-separated format are repeated from the schema, which is minor redundancy for a paid tool.

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?

Despite an output schema existing, the description adds crucial interpretive guidance: data is an array of code/ok/data-or-error entries with requested/returned/failed counts. Combined with the paywall, cap, and market-coverage disclosures, an agent has everything needed to call it correctly and interpret partial failures.

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 format semantics beyond the schema: comma-separated lists, bare 6-digit codes (000099) are accepted in addition to prefixed codes (sz000099), and it reiterates the tier-based count limits. This meaningfully reduces malformed-input risk.

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 verb and resource in the opening line: batch fund flow for multiple stocks, covering main funds + LHB + block trades + margin trading, one record per stock. It explicitly names the sibling it differs from (ashare_fund returns one stock; this returns many), so an agent can select it 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 gives concrete user-question triggers ('these stocks' fund flow', 'scan my pool's main funds', 'which stocks in an industry have inflows') and a direct exclusion rule versus ashare_fund. When to use and when not to use are both explicit.

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