scroll

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

With no annotations, the description carries full burden but fails to disclose behaviors such as whether scrolling is absolute or relative (x,y vs deltaX,deltaY), what happens with invalid coordinates, or if scrolling to an element requires a specific parameter. The description is too vague.

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 short (one sentence), which is efficient, but lacks any structure to convey the two modes of scrolling (absolute and relative) and element targeting. Could be more organized.

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 7 parameters and no output schema, the description is incomplete. It does not explain the difference between absolute and relative scrolling, the use of selector vs ref, or the purpose of tabId. The complexity of the tool is not addressed.

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 only 43%, with only ref, tabId, and selector described. The description adds no meaning to parameters like x, y, deltaX, deltaY. It does not clarify that x,y are absolute and deltaX,deltaY are relative offsets.

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 verb 'scroll' and the target ('page or an element'). It distinguishes from sibling tools like 'click' or 'navigate' by specifying scrolling. However, it does not differentiate from any potential scrolling alternatives among siblings, which are absent anyway.

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 on when to use this tool versus alternatives like 'click' or 'navigate'. The description gives no context for appropriate usage or when to avoid.

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