订单簿深度

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

The annotations readOnlyHint=true and openWorldHint=true already convey the read-only, potentially changing nature of the data, and the description does not contradict them. The description adds meaningful behavioral guidance beyond the annotations by constraining limit to legal values (5/10/20/50/100/500/1000), which the schema leaves effectively unbounded. It does not describe the ordering of the bid/ask sides, a minor gap for a read-only snapshot tool.

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: one clause establishes the action, one clause delivers the parameter constraint. Every sentence earns its place, and the most decision-relevant information (legal limit values) is front-loaded immediately after the purpose.

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 two simple parameters, a read-only and open-world annotation set, and no output schema, the description covers what the agent needs in order to invoke the tool correctly: the supported symbol and the admissible limit values. A short note on return shape (e.g., sides/ordering) would be a nice addition since no output schema exists, but it is not blocking for a basic snapshot call.

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?

At 0% schema description coverage, the description compensates well: the phrase '指定交易对' explains what the symbol parameter means, and the explict enumeration of legal limit values (5/10/20/50/100/500/1000) provides far more precision than the schema's meaningless numeric bounds. It does not explain whether the limit applies to each side or the total depth, but the core meaning of both parameters is in place.

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 a specific action and resource: '获取指定交易对的买卖盘快照' (fetches a snapshot of the order book for a specified trading pair). It is unambiguous about which resource it concerns, though it does not explicitly contrast itself with the similarly named sibling market_book_ticker.

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?

There is no when-to-use or when-not-to-use guidance. The description never explains why an agent should choose this tool instead of market_book_ticker (best bid/ask) or market_klines (candles); an agent is left to infer the use case from the tool name and purpose alone.

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