get_block_trades

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

No annotations are provided, so the description carries the full burden. It does not disclose any behavioral traits such as data source, update frequency, pagination, error conditions, or rate limits. The description is purely descriptive of the content type without any indication of side effects, performance implications, or data retrieval specifics.

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 concise and efficiently conveys the core purpose in one line followed by a parameter list. It is front-loaded with the main content description. The parameter documentation is minimal but sufficient for basic understanding. No extraneous content.

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?

The tool has a simple input (2 parameters) and an output schema exists (though not shown in detail). For a data retrieval tool like this, the description gives the essential purpose and parameter meanings. It lacks guidance on typical use cases or output interpretation, but with an output schema available, the agent can infer the return structure. The main gaps are usage guidelines and behavioral disclosures.

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?

With 0% schema description coverage, the description must compensate, but it only provides 'Args: symbol: 股票代码, count: 取最近几笔，最多 50'. This clarifies that symbol is a stock code and count is the number of recent trades (max 50), which adds meaning beyond the bare schema. However, it does not explain the format of symbol (e.g., exchange prefix), the default behavior if count is omitted, or the meaning of 'recent' in terms of time periods.

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 states '大宗交易明细' (block trade details), specifying the resource. It mentions 成交价 (transaction price), 折溢价率 (discount/premium rate), and 买卖双方营业部 (trading departments of both parties). However, it does not provide explicit differentiation from sibling tools like get_quote or get_capital_flow, though the specific details mentioned distinguish it sufficiently.

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?

The description provides no guidance on when to use this tool versus alternatives. There is no mention of scenarios, prerequisites, or exclusions. Sibling tools like get_capital_flow and get_quote might be alternatives for different types of trading data, but no such comparisons are made.

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