Brings a target element into view via a snapshot ref or CSS selector, or shifts the viewport by X/Y coordinates in a browser tab.
Scroll an element into view, or by x/y.
| Name | Required | Description | Default |
|---|---|---|---|
| x | No | ||
| y | No | ||
| ref | No | ref from snapshot, e.g. e3 | |
| tab | No | tab id, defaults to current | |
| selector | No | CSS selector | |
| request_timeout | No | Outer page request deadline in milliseconds; defaults to at least 30000 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the full burden and falls short: it does not say which surface scrolls, what happens when neither mode is supplied, which takes precedence if both are, or whether scrolling waits for completion. The mode split is the only real behavioral disclosure.
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 with no filler. Brevity is appropriate, though it is under-specified rather than tight.
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?
Six optional parameters, no annotations, and no output schema — the description should explain precedence between element and coordinate modes and the default behavior with no arguments. Neither is covered, leaving real ambiguity for a zero-required-parameter tool.
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 67% and the description only implies semantics for ref/selector (element mode) and x/y (coordinate mode); selector, tab, and request_timeout get nothing extra from the description. Roughly baseline for partial coverage.
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 the two targeting modes (element into view, or by x/y), which is enough to distinguish it from every sibling in the list — none of which scroll. Lacks any statement of target surface (page vs. scrollable container).
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?
No when-to-use guidance, no prerequisites, and no indication of which mode to pick when — though the two modes are named. An agent has to infer that ref/selector selects element mode and x/y selects pixel mode.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.