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

With no annotations, the description carries the full disclosure burden and does: read-only, update cadence tied to disclosure dates with a note that missing periods are not a fault, HK support, and a warning not to hard-parse HK column names against A-share conventions. It also reveals the return shape (three tables in fixed index order, descending by period).

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 core purpose, then grouped warnings; every warning carries distinct information (table order, sibling routing, refresh cadence, HK parsing). Dense with repeated ⚠️ markers and bold, which is slightly noisy, but there is little outright filler.

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 the one thing the schema cannot convey cheaply: which index is which statement and the descending period ordering. Combined with the freshness caveat and HK caveat, an agent has everything needed to call and interpret 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 baseline is 3; the description adds real meaning on top by characterizing num as '最近 N 期' and, more importantly, documenting the HK code format `hk00700` that the schema's example (`sh600667`) does not cover. It stops short of spelling out edge cases such as num=0 or the maximum value.

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 verb and resource set (利润表/资产负债表/现金流量表, 最近 N 期) and explicitly maps conversational intents (营收/净利润/毛利率/负债) to this tool. It is clearly distinguishable from valuation siblings by the note that PE/PB belong elsewhere.

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 explicit when-to-use triggers ('用户问…用这个') and explicit when-not-to-use with named alternatives (ashare_sector_valuation / ashare_quote 的估值字段). The exclusion is unambiguous, so an agent can route without guessing.

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