Scroll

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

No annotations are provided, so the description carries the behavioral burden. It usefully discloses the default action point (current mouse location) and the non-obvious direction convention (dy negative = down), but omits scroll magnitude, focus/foreground requirements, and animation/completion behavior.

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?

Two tightly packed sentences that front-load position and direction rules with zero filler. Each clause earns its place.

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 7-parameter, no-annotation, no-output-schema tool this is thin. The direction convention is covered, but an agent still lacks guidance on scroll amount and modality (image vs screen coordinates are left to the schema), leaving gaps for correct invocation.

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%, so the description must compensate. It adds crucial meaning to dy/dx (sign convention, lines unit) that the bare integer schema does not, but dx is only vaguely described as 'for sideways' and x/y, image, screen, and look_after rely entirely on the schema.

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?

States a specific verb (Scroll) and the resource/position model (x/y mouse position), which is concrete. It does not differentiate itself from the sibling browser_scroll, but for a low-level input primitive the action is unambiguous.

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?

Provides direction semantics but nothing about when to use this scroll vs browser_scroll, how many lines a call scrolls, whether it can be repeated, or whether the target window must be focused. No alternatives are named.

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