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

With no annotations provided, the description fully carries the behavioral transparency burden. It discloses that the tool is read-only, returns exactly three tables in a fixed order (data[0], data[1], data[2]), sorts periods descending (latest first), and explains update cadence (only after financial disclosures, absence of new data is not a bug). This is comprehensive and beyond typical description detail.

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?

The description is compact yet information-dense, front-loading the core purpose and following with crucial warnings in a structured way. Every sentence earns its place: purpose, return format, sibling differentiation, and update behavior. The use of warnings (⚠️) highlights critical operational details without bloat.

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?

Given the tool's complexity (three return tables) and the existence of an output schema, the description still adds essential orientation: table indices, ordering, and update timing. It also covers when to choose alternate tools, so an agent can invoke this tool correctly without further research. Complete for selection and invocation.

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 description coverage is 100%, so the schema already documents both parameters clearly (code format and num period count). The description adds the concept of '最近 N 期' (recent N periods) and the descending order, but these are more behavioral than parameter-specific. Since the schema handles parameter meaning, a baseline 3 is appropriate; the description does not meaningfully extend parameter semantics beyond the schema.

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 clearly identifies the tool as providing financial statements (income statement, balance sheet, cash flow statement) for the most recent N periods, and distinguishes it from sibling tools by stating when to use it ('营收/净利润/毛利率/负债/财务数据') and which alternatives cover valuation multiples. This gives an agent a precise selection criterion.

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?

Explicit when-to-use guidance is given: for revenue, net profit, gross margin, liabilities, or financial data. It also explicitly states what NOT to use it for (valuation multiples PE/PB) and names the correct alternatives (ashare_sector_valuation or ashare_quote valuation fields). This is textbook usage differentiation.

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