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 declares read-only behavior, quarterly (not daily) data freshness, HK-only coverage, and a subscription-tier gate. It does not mention historical depth/earliest available quarter or pagination, which are the remaining behavioral unknowns.

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 the resource and fields, then usage trigger, then the disambiguation warning — good ordering with little waste. Slightly over-signposted with bold and ⚠️ markers, and the comma-separated codes note duplicates the schema.

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, so return values need not be described, and the definition covers scope, cadence, access tier, and the nearest alternative. Missing only minor details such as how far back quarterly data goes or what an empty result means for a non-southbound code.

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% (both date and codes are documented in the schema), so the baseline is 3. The description's note that 'codes 可逗号多只' merely repeats the schema's '港股代码，逗号分隔' example and adds no new meaning, and the date parameter is not discussed at all in the description.

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 (港股通南下资金持仓) with its cadence (季度) and the exact fields returned (持股数/持股比例/持股市值). It also delimits scope (仅港股), so an agent can separate it from ashare_fund_flow and the other fund-related siblings 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?

Gives an explicit triggering question pattern ('南下资金持有多少/港股通占比'), an explicit exclusion (quarterly holdings, not daily flow), and names the alternative tool ashare_fund_flow for the daily case. It also flags the Pro-tier (¥99+) access prerequisite, which is guidance an agent needs before promising a result.

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