stock_zh_index_hist_csindex

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

The description discloses a key behavioral trait beyond annotations: it only provides closing prices ('只有收盘价') and returns a DataFrame with date and close price. This adds context about data limitations. Annotations already declare read-only and idempotent hints, so the description complements rather than repeats them. No hidden side effects or rate limits are mentioned, but the safety profile is covered.

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 structured with a title, a crucial P.S. note, a reference URL, and docstring-style parameter explanations. It is not overly long and each part adds value: the P.S. carries the most important usage caveat, the URL provides a source reference, and docstrings define parameters. The content is front-loaded with the caveat right after the title, making it easy to scan.

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 relatively simple read-only tool with three parameters, the description covers the essential context: what data is returned (dates and closing prices), when to use it (only for indices exclusive to CSIndex), and parameter meanings. It lacks a few details like date format, but defaults and examples fill that gap. No output schema exists, so the return description is sufficient.

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 schema provides no descriptions for the three parameters (coverage 0%), but the description includes docstrings explaining each: symbol is the index code with an example, start_date and end_date are start/end dates (format implied by defaults). This effectively compensates for the schema gap. It does not specify date format explicitly, but the defaults in the schema (e.g., 20240604) make it clear.

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 retrieving historical market data for a specific CSI index ('中证指数-具体指数-历史行情数据'). The P.S. adds that it only returns closing prices and normally shouldn't be used unless the index is exclusive to the CSIndex website, which distinguishes it from other index data tools. However, it lacks an explicit action verb like 'fetch' or 'get', relying on the noun phrase to imply the purpose.

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 P.S. provides explicit guidance on when to use this tool: '正常情况下不应使用该接口，除非指数只有中证网站有' (normally should not use this interface unless the index is only available on the CSIndex website). This clearly states a when-not condition and implies alternatives, but it does not name specific alternative tools, stopping 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.