stock_yjbb_em

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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds the return type (pandas.DataFrame) and date format constraints, which are useful. However, it does not disclose potential behaviors like error handling for invalid dates or data availability ranges beyond the start date.

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 compact but poorly structured: it starts with a category path, then a URL, then parameter/return lines. It could be more front-loaded with a clear one-sentence purpose. The URL is arguably unnecessary for an AI agent. Every line provides some info, but the ordering and formatting hurt readability.

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 simple one-parameter tool, the description offers return type and date constraints, but it leaves key context ambiguous: what exactly '业绩报表' contains, whether the date represents the report period end or announcement date, and how it differs from adjacent tools. With no output schema, the description should clarify the data structure or at least the meaning of the date. It falls short.

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 offers no description for the 'date' parameter (0% coverage), so the description must compensate. It does so by providing explicit valid examples ('20200331', '20200630') and a lower bound ('从 20100331 开始'), which gives the agent actionable format and range information. It stops short of explaining that these are quarter-end dates, but the examples strongly imply it.

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 is essentially a breadcrumb path ('东方财富-数据中心-年报季报-业绩快报-业绩报表') and the return type '业绩报表', which restates the tool name. It lacks a clear verb or explicit statement like 'Retrieves performance reports from East Money for a given date.' The purpose is implied but not clearly articulated.

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 parameter constraints (valid date formats, starting from 20100331) but offers no guidance on when to use this tool versus similar siblings like stock_yjkb_em or stock_yjyg_em. No alternatives or exclusions are mentioned.

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