scroll

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

With no annotations, the description carries full burden. It details behaviors: raw sends wheel notches at coordinates, to_element requires UIA ScrollItemPattern, smart handles nested scroll layers, capture stitches images (with caveat on pixel coords when sizeReduced=true), read uses OCR with imperfect accuracy. It also notes preconditions like window visibility and browser_open requirement.

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 relatively long but well-structured into Purpose, Details, Prefer, Caveats, and Examples. It is front-loaded with the core purpose. Each sentence adds value given the complexity of 5 actions. Could be slightly more concise, but the structure aids readability.

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 high complexity (5 actions, many parameters) and 100% schema coverage, the description is largely complete. It covers behaviors, usage, and caveats. Missing explicit return types for some actions (raw, to_element, smart) beyond mentioning image and text for capture/read. The 'include' parameter hints at envelope shape. Overall, a minor gap.

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 100%, so baseline is 3. The description adds significant value by explaining parameters in context (e.g., 'action=\"raw\": send raw mouse-wheel notches at (x,y)', 'action=\"smart\": handles nested scroll layers, virtualised lists'). It also clarifies abstract concepts like 'homing' and 'sizeReduced=true' meaning downscaled. However, some parameter details are already in the schema, so slight redundancy.

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 'Scroll a window or page' and enumerates 5 distinct strategies (raw, to_element, smart, capture, read). It differentiates from siblings like browser_click or mouse_click by focusing solely on scrolling, and provides specific use cases for each strategy.

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 'Prefer' section explicitly tells when to use each action (e.g., 'Use action=\"to_element\" or action=\"smart\" for click target out-of-viewport recovery'). Caveats provide clear when-not-to-use (e.g., 'action=\"capture\" ... use for reading only, not mouse_click'). Alternatives like browser_eval and browser_overview are mentioned for browser text extraction.

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