scroll_start

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

With no annotations provided, the description carries full burden. It mentions the tool returns a scroll_id for subsequent retrieval, which is useful behavioral context. However, it doesn't disclose important traits like whether this is a read/write operation, performance implications, error conditions, or how the scrolling mechanism works. The description adds some value but leaves significant gaps for a tool that initiates data traversal.

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 efficiently structured with a purpose statement followed by a parameter list and return value note. Each sentence serves a clear purpose, though the formatting with line breaks could be cleaner. The information is front-loaded with the core functionality stated first.

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 tool with 5 parameters, no annotations, no output schema, and complex functionality (initiating scroll searches), the description provides basic purpose and parameter semantics but lacks details about the scrolling mechanism, error handling, performance considerations, and how it integrates with 'scroll_next' and 'scroll_clear'. It's minimally adequate but has clear gaps for proper agent understanding.

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?

With 0% schema description coverage and 5 parameters, the description compensates well by listing all parameters with Chinese labels: 'index: 索引名称', 'query: 查询条件', 'size: 每批数量', 'scroll: 滚动上下文保持时间', 'sort: 排序规则'. This provides semantic meaning for each parameter beyond what the bare schema offers, though it doesn't explain format details or constraints.

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's purpose: '开始滚动搜索（用于遍历大量数据）' translates to 'Start scrolling search (for traversing large amounts of data)'. This specifies the verb ('start scrolling search') and resource ('large amounts of data'), though it doesn't explicitly differentiate from sibling tools like 'search' or 'search_simple' beyond mentioning scrolling.

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 implies usage context ('用于遍历大量数据' - for traversing large amounts of data) and mentions a return value ('返回 scroll_id 用于后续获取' - returns scroll_id for subsequent retrieval), which hints at its role in a multi-step process. However, it doesn't explicitly state when to use this versus alternatives like 'search' or how it relates to sibling tools 'scroll_clear' and 'scroll_next'.

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