Scroll web pages or specific containers in any direction, to the top or bottom. Provide an element ID to scroll that container instead of the window.
Scrolls in a direction or to the top/bottom. When an element id is given, scrolls that container instead of the window.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | No | Scroll steps for relative directions. | |
| clientId | No | Optional target page. | |
| direction | No | down | |
| element_id | No | Optional container element id to scroll. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the container-vs-window default behavior, but says nothing about whether the scroll is animated/awaited, whether lazy-loaded content is triggered, or what is returned (no output schema exists). Permission or rate concerns are also unaddressed, though these are less critical for a UI-scroll 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?
Two short sentences, zero filler, with the primary behavior front-loaded and the conditional container behavior second. Nothing is padded or repeated from the schema.
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 4-parameter browser-automation tool this covers the core behavior adequately, but it omits return information, the meaning of an 'amount step', and how it interacts with the surrounding automation flow. With no annotations and no output schema, a little more disclosure would meaningfully help an agent call it correctly.
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%, so the baseline is 3. The description does add real meaning by explaining that element_id redirects the scroll target from the window to a container, but it leaves 'amount' underspecified — the schema calls it 'scroll steps' while the description never clarifies what a step is in pixels or how it interacts with the top/bottom enum values.
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 its two modes: directional/top-bottom movement, and container-targeted movement when an element id is supplied. This is clearly distinct from the listed siblings (click_element, input_text, get_dom_tree, list_pages), though the description never explicitly names or contrasts them.
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?
Usage is only implied — the agent can infer this is the way to bring off-screen content into view before reading the DOM or clicking, but the description never says when to use this versus get_dom_tree or when a scroll is unnecessary. No exclusions or prerequisites are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.