scroll_next

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

No annotations are provided, so the description carries full burden. It mentions '滚动上下文保持时间' (scroll context retention time) in the parameter list, hinting at time-limited behavior, but doesn't disclose critical traits like whether this is read-only, pagination mechanics, error conditions, or rate limits. For a tool that likely handles result pagination, this is insufficient behavioral context.

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 brief with a purpose statement and parameter list, but the structure is basic and not front-loaded with critical information. The parameter section repeats what's in the schema without adding value, making it somewhat wasteful. However, it avoids excessive verbosity.

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 2 parameters with 0% schema coverage, no annotations, no output schema, and sibling tools indicating this is part of a scrolling system (e.g., with scroll_start, scroll_clear), the description is incomplete. It lacks explanation of the scrolling workflow, return values, error handling, or integration with other tools, leaving significant gaps for an AI agent.

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?

Schema description coverage is 0%, so the description must compensate. It lists parameters with brief Chinese labels ('滚动 ID' for scroll_id, '滚动上下文保持时间' for scroll), adding minimal semantic value beyond the schema's property titles. No details on format (e.g., scroll_id structure, scroll time units like '5m'), constraints, or examples are provided, leaving parameters poorly documented.

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 states '获取下一批滚动结果' (get next batch of scroll results), which provides a basic verb+resource combination. However, it doesn't distinguish this from sibling tools like 'scroll_start' or 'scroll_clear', nor does it explain what 'scroll results' means in this context. The purpose is understandable but vague about the specific domain (likely Elasticsearch 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?

No guidance is provided about when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., needing a scroll_id from scroll_start), exclusions, or comparisons to similar tools like search or msearch. The agent must infer usage from the tool name and parameters alone.

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