compare_stocks

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

The description adds value beyond annotations by specifying the returned data types (real-time quotes, MA/MACD indicators) and the '侧併' (side-by-side) format. Since annotations already declare readOnlyHint=true and openWorldHint=false, the bar is lower. However, it does not disclose potential caveats such as data latency, maximum symbol count beyond schema, or behavior for invalid symbols.

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, well-structured sentence that conveys the tool's core value proposition upfront. It uses the '【复合】' prefix to denote composite functionality and avoids redundant filler, earning a perfect score for conciseness.

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 read-only comparison tool with no output schema, the description adequately covers the key return elements (real-time quotes and MA/MACD indicators). It is complete enough for an agent to select and invoke the tool. The lack of details like ordering, timezone, or error handling is a minor gap given the tool's moderate complexity, hence a 4.

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 already provides descriptions for both parameters ('symbols' as stock code array 2-10, 'period' as K-line period enum). Schema description coverage is 100%, so the baseline is 3. The description adds minimal parameter-level context beyond what the schema conveys, merely hinting at 'multiple stocks' and 'recent indicators' without elaborating parameter usage.

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?

Description explicitly states it performs multi-stock comparison analysis, returning real-time quotes and recent indicators (MA/MACD) side-by-side. The verb '返回' (returns) and resource '多只股票的实时行情和近期指标' clearly define the tool's function and distinguish it from single-stock quote/kline tools among siblings.

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 clearly conveys the context: use this tool when you need a one-time side-by-side comparison of multiple stocks with quotes and indicators. However, it does not explicitly mention alternative tools (e.g., get_kline_with_indicators for single-stock indicator analysis) or exclusion criteria, so it earns a 4 rather than a 5.

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