Scroll with the wheel

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

Annotations only mark readOnlyHint=false, so the description does real work: it discloses that real wheel events are dispatched at the BiDi layer and explains the inner-container scrolling behavior that a naive scrollTop approach would miss. It is consistent with readOnlyHint=false (scrolling mutates viewport state), though it doesn't describe the return value or whether the resulting scroll position is reported.

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?

Three tight sentences, front-loaded with what the tool does, then parameter semantics, then the key selector caveat. Every sentence contributes and none restates the schema verbatim without adding meaning.

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 4-parameter, no-output-schema tool with thin annotations, the description covers mechanism, units, direction, defaults (via schema), and the selector caveat well. The only gap is that it doesn't say what the call returns or whether scroll position is observable afterwards.

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 already 100%, so the baseline is 3. The description adds semantic value beyond the schema by explaining sign convention (positive Y scrolls down), pixel units, and, importantly, the behavioral meaning of selector beyond the schema's terse 'Scrollable element to aim at' — that it aims wheel events at inner overflow containers.

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 resource (the page or one scrollable element) and identifies the mechanism, 'real wheel events (BiDi input.performActions type "wheel")'. This clearly separates it from sibling input tools like browser_press_key or browser_mouse_action without needing to open the schema.

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?

Explicitly explains the selector/no-selector choice: with a selector the wheel is aimed at that element, which is required for inner overflow containers since document.scrollTop never moves for those. It gives clear context for when this tool is needed but stops short of naming alternatives such as keyboard-based PageDown scrolling.

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