Scroll the current document by pixels or to top/bottom, or bring a referenced element into view; take a fresh snapshot afterward because scrolling may load data.
Scroll the current document up/down/left/right by 1-10000 pixels, or to top/bottom. direction=into_view requires a fresh visible reference; other directions reject ref. Scroll handlers may load data; take a fresh snapshot.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | ||
| pixels | No | ||
| direction | No | down |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the 1-10000 pixel range, ref acceptance/rejection by direction, and the important side effect that scroll handlers may load data. The main omission is whether the call itself returns any result or waits for loading to complete.
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 the main action, then the special into_view/ref rule, then the post-scroll snapshot advice. Every sentence carries useful information with no repetition.
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 three-parameter browser tool with no annotations, no output schema, and 0% schema description coverage, the description is nearly complete. It covers invocation semantics and side effects; only minor details like return behavior or wait semantics are left implicit.
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 description coverage is 0%, so the description must compensate, and it largely does: it defines the direction values (up/down/left/right/top/bottom/into_view), the pixel range, and the ref requirements. It does not state the default direction, default pixel count, or exact ref format, but the core semantics are covered.
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 uses a specific verb and resource: scrolling the current document in all four directions, to top/bottom, or into view. It also scopes the pixel range, making the tool's purpose immediately distinguishable from navigation and snapshot siblings.
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?
It clearly states the conditions for direction=into_view versus other directions, including that into_view requires a fresh visible reference while other directions reject ref. It also advises taking a fresh snapshot after scrolling, though it does not explicitly name alternatives such as browser_snapshot or browser_navigate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.