Move a web page's visible area by horizontal or vertical pixel amounts, or reveal a target element within the open browser tab.
Scroll the page by dx/dy pixels (positive dy = down, positive dx = right), or scroll an element into view when selector is given.
| Name | Required | Description | Default |
|---|---|---|---|
| dx | No | Pixels to scroll horizontally (default 0) | |
| dy | No | Pixels to scroll vertically (default 600) | |
| tabId | No | ||
| selector | No | Scroll this element into view instead |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full behavioral burden, but it only discloses direction semantics and dual modes. It omits timing (instant vs. smooth), side effects on page state, failure behavior when a selector is not found, and which tab is affected. This is a significant gap for a browser automation tool.
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?
A single, front-loaded sentence that packs the two modes and direction semantics without any filler. Every 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 simple scroll tool, the description covers the primary invocation paths, and the schema supplies defaults for dx and dy. However, with no annotations and no output schema, the omission of tabId semantics and scroll behavior leaves minor gaps an agent must infer.
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 75%, and the description adds critical meaning beyond the schema by defining sign conventions: positive dy scrolls down and positive dx scrolls right. The selector mode is also restated usefully, though tabId remains undocumented in both places.
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 ('page' or 'element'), and clarifies two modes: pixel scrolling and element-into-view. It does not explicitly differentiate itself from sibling tools like 'navigate' or 'click', but the purpose 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?
The description explains two internal modes (pixel scrolling vs. selector-based scrolling) but gives no guidance on when to use this tool instead of alternatives such as 'navigate', 'click', or 'snapshot'. No prerequisites, exclusions, or sibling routing are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.