stock_hold_change_cninfo

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which conveys the safety profile. The description adds the source URL and the fact that it returns a DataFrame, but discloses no additional behavioral traits such as pagination, data granularity, or rate limits. With annotations covering the core safety behavior, 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 written as a compact docstring with a title line, URL, parameter/return annotations, which is reasonably sized for a one-parameter tool. However, it lacks a plain-language opening sentence and front-loads the Chinese title, making it less immediately scannable. Each line contributes something, but the structure is not optimally tailored for an AI agent's quick parsing.

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's simplicity (one optional parameter) and annotations indicating a safe read operation, the description gives enough to invoke it. Yet it does not describe the contents of the returned DataFrame beyond '股本变动', nor does it explain the relationship to sibling tools like stock_share_change_cninfo, leaving some ambiguity for selection and output expectation. It is adequate but incomplete for a tool with many close relatives.

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 only defines 'symbol' as a string with a default, providing no descriptions. The description compensates by listing the valid choices: {"深市主板", "沪市", "创业板", "科创板", "北交所", "全部"}, which adds meaningful semantic value beyond the schema. It also documents the parameter type and return type, though it does not explain what each market choice specifically filters or the exact output columns.

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 '股本变动' (capital stock changes) from CNInfo's data center, and the Chinese title and URL clarify the source. It is specific about the resource (thematic statistics for shareholders' equity) and the return type (pandas.DataFrame). However, it does not explicitly differentiate itself from sibling tools like stock_share_change_cninfo or stock_hold_num_cninfo, so it misses the top score.

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 no guidance on when to use this tool versus alternatives like stock_hold_control_cninfo or stock_share_hold_change_sse. It only lists the parameter choices and the return type, with no context about use cases, prerequisites, or exclusions. Given the large number of related stock-hold/share tools, this lack of usage guidance is a notable gap.

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