get_margin_data

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only nature is covered. The description adds useful context: the distinction between account and target types, and that date defaults to the latest trading day when type=target. However, it does not disclose response format, pagination, or edge cases (e.g., behavior when date is provided for account type). This is adequate but not rich.

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 a single concise sentence, front-loaded with the main purpose and followed by a colon-delimited breakdown of the type parameter. Every word contributes to understanding, with no redundant or filler content. It is appropriately sized for the tool's simplicity.

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 has only two parameters, no output schema, and straightforward read-only behavior, the description covers the essential semantics: what it does, the two modes, and the optional date context. It does not describe the return structure, but for a data-retrieval tool with simple inputs, this is not a critical gap. The description is sufficiently complete for an agent to select and invoke the tool correctly.

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%, with descriptions for both parameters. The description adds meaning beyond the schema by elaborating on what each type returns: account includes market-wide balance and trends, target includes stock-level data. This extra detail helps agents understand the semantic difference between enum values, going beyond the baseline for fully-covered schemas.

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 the tool retrieves margin trading data (融资融券数据) and distinguishes between two modes: account-level statistics (全市场两融余额和融资/融券趋势) and target-level stock details (个股级别的融资融券数据). This specific verb-resource pairing and mode breakdown make it distinct from all sibling tools, none of which mention margin trading.

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 implies usage by explaining when each type is appropriate (account for market-wide trends, target for stock-level data). However, it does not explicitly mention when not to use this tool or alternatives, such as using kline tools for price data. The context is clear but lacks formal exclusions or alternative references, so it falls short of a 5.

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