stock_hold_control_cninfo

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

Annotations already provide readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds the data source and a note that data starts from 2010, which is useful context beyond the annotations. However, it does not disclose any additional behavioral traits such as rate limits, pagination, or data granularity, and there is no contradiction with the annotations.

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 compact docstring with clear sections for param and return, making it easy to parse. It includes a URL that may be extraneous but is not overly verbose. It is relatively front-loaded with the source path, though it lacks a single crisp one-liner summarizing the action. Overall, every sentence earns its place except the URL could be trimmed.

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 one simple parameter and the annotations cover safety, the description is mostly complete: it states the data source, parameter choices, and return type (pandas.DataFrame). No output schema exists, so the return type disclosure is important. The phrase '从 2010 开始' is somewhat ambiguous (whether it refers to the start date of data or a parameter constraint), and the description does not detail the DataFrame's columns or other edge cases, but for a simple retrieval tool this is adequate.

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 input schema provides no description for the symbol parameter and no enum values. The description fully compensates by enumerating the exact allowed choices: 单独控制, 实际控制人, 一致行动人, 家族控制, 全部. It also hints at the data period starting 2010. This is essential information for correctly selecting and invoking the tool, making the description highly effective for parameter understanding.

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 resource: 实际控制人持股变动 (actual controller shareholding changes) from 巨潮资讯 cninfo data center thematic statistics. It specifies the return type as pandas.DataFrame. However, it uses a noun phrase rather than an explicit imperative verb like 'get' or 'query', and does not explicitly distinguish itself from sibling tools such as stock_hold_change_cninfo, though the subject matter is distinct.

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 context about the data source and topic, implying it should be used when actual controller shareholding changes are needed. It also lists valid symbol choices. However, it does not explicitly state when to use it versus alternatives, nor does it mention any exclusions or prerequisites, leaving usage guidance largely implicit.

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