scroll_wheel

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

The description notes the fire-and-forget behavior and that it no longer times out after the fix, which is useful behavioral context. With no annotations present, the description carries the burden but only partially covers it — it doesn't disclose the compositor-level side effects (e.g., it bypasses JS event listeners?), whether events are coalesced, or what the return value is.

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 — two sentences — but the second sentence is a fragment about a past bug fix ('fire-and-forget 修复后...不再超时') which is low-value implementation history rather than usage guidance. The example call is useful but the cryptic phrasing costs efficiency.

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 4-param no-schema-coverage tool with no annotations and no output schema, this description is insufficient. It doesn't explain the parameter semantics, scroll direction conventions, coordinate system, or return behavior. The unique CDP aspect is mentioned but the operational details needed to invoke it correctly are largely missing.

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 coverage is 0%, so the description must compensate for undocumented parameters. The description shows an example call 'scroll_wheel(0, 500)' but there are 4 parameters (x, y, dx, dy) — it doesn't explain which args the example maps to, what the coordinate semantics are, or what dx/dy mean. The example is ambiguous about whether (0, 500) means x=0, dy=500 or something else. Significant gap for a 4-param tool.

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 indicates it's a CDP compositor-level mouseWheel event that can penetrate iframe/shadow DOM, distinguishing it from sibling scroll tools like scroll_to and scroll_into_view. It names the underlying mechanism (Input.dispatchMouseEvent) and its unique capability (iframe/shadow DOM penetration). However, it doesn't explicitly say 'scroll the page' in plain terms and leans on technical jargon.

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 this tool should be used when iframe/shadow DOM penetration is needed, implicitly distinguishing it from other scroll tools. However, it doesn't explicitly state when to use it vs alternatives like scroll_to or scroll_into_view, nor does it state when NOT to use it. The 'fire-and-forget' note hints at a behavior difference but provides no clear usage direction.

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