账户总览

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

Annotations (readOnlyHint, idempotentHint, openWorldHint) already cover the safety profile, so the description's burden is low. It adds one useful fact: the response is an aggregated 汇总 of wallet/UP/L/margin. It does not reveal whether the numbers are real-time, cached, or aggregated across all account assets, but for a simple read-only overview the output schema likely covers that - the description also completes the annotations without any attribution.

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?

One short sentence, front-valued verb and enumerated result categories, and no fluff. The Chinese phrasing is compact and precise; every element earns its line space. Even the title and description together leave no repetition.

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?

For a zero-parameter, read-only, idempotent tool with an output schema, this definition is nearly complete: an agent can sed it and understand what should come back (the summary categories), since schema/annotations cover the rest. The one missing piece is an explicit relation to sibling trading_balance to prevent picking the wrong account tool, but given the tool's low complexity, this is a small omission.

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?

The tool admits zero parameters, so the baseline for parameter semantics is 4; there is nothing the description needs to document. The field list (wallet balance, unrealized P&L, margin) tellingly shapes the no-arg call's result, which is all the param-aware an agent can ask given an empty 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 states a specific verb ('返回' - returns) plus the resource: wallet balance, unrealized P&L, margin summaries. It clearly conveys an account-overview aggregation, reinforced by the title 账户总览. It does not explicitly distinguish itself from sibling tools such as trading_balance, so it falls a step short of 5.

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 guidance on when to invoke this tool versus alternatives, and with dozens of trading siblings including trading_balance, trading_positions, trading_position_mode, and trading_position_margin, an agent gets no routing hint because it is a summary-use it. The 'when-to-use' must be completely inferred, so this is effectively implied-only minimal formulation.

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