scroll

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

With no annotations, the description carries full burden. It details humanization behavior (varied scroll chunks, micro-pauses, reading pause chance) and the underlying mechanism (CDP events). Missing potential traits like overflow handling or smoothness, but sufficiently transparent.

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, well-structured with bullet points, and front-loaded with the key differentiator (CDP events). Every sentence adds value without repetition.

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?

While the description covers the tool's purpose and stealth feature, it does not detail all parameters (amount missing) or return value (output schema exists but not explained). For a tool with 3 parameters, more completeness is warranted.

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 description must compensate. It mentions direction and humanize booleans but omits the 'amount' parameter entirely. This partially explains parameters but leaves a gap for the amount field.

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 scrolls a page using real mouse wheel events, distinguishing it from JS-based scrolling. It specifies the resource (page) and verb (scroll), and implicitly differentiates from sibling 'scroll_to' by emphasizing CDP events for stealth.

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 context on when to use humanize (for bypassing detection) vs non-humanized (for speed), and lists directions. However, it lacks explicit guidance on when to avoid this tool or compare with alternatives like 'scroll_to'.

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