scroll

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

No annotations provided, so the description must disclose behavior. It adds that a screenshot is returned after scrolling, which is valuable. However, it omits details on scrolling behavior (smooth/instant), handling of iframes, error states for missing selectors, or effect of the url parameter.

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 sentences packed with essential information: action (scroll), modes (pixel or element), and output (screenshot). No wasted words.

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 the four optional parameters and no output schema, the description is mostly complete: it explains the two scroll modes and the screenshot return. Minor missing details like what happens if toSelector fails or if amount exceeds page length, but adequate for typical use.

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?

Input schema has 100% description coverage, so the baseline is 3. The description does not add extra meaning beyond the schema for parameters, but the overall purpose of returning a screenshot is separate.

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 by pixel amount or to an element and returns a screenshot. It distinguishes itself from siblings like navigate (which goes to URLs) and click (which interacts), but does not explicitly differentiate from any similar scrolling tool, as none exist.

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 usage when scrolling is needed with visual verification, but lacks explicit 'when to use' vs 'when not to use' or alternatives. The presence of toSelector vs direction/amount suggests two modes, but no guidance on choosing between them.

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