Skip to main content
Glama

browser_scroll

Scroll a web page or specific element by CSS pixels, optionally targeting a tab, frame, or element reference to reach off-screen content or trigger lazy loading.

Instructions

Scroll the page or an element by CSS pixels.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tabId": "<tabId>"
    },
    "name": "browser_scroll"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
refNoElement ref from the latest snapshot in this document.
pagesNo
tabIdYesTab id from browser_tabs.
expectNoPost-action condition. Default timeout is 1.2 seconds in visible pages and 3 seconds in hidden pages. A mismatch does not undo the action; inspect before retrying.
originNo
browserNoBrowser id from browser_list, or chrome/firefox when only one instance matches.
frameIdNoFrame id from browser_frames; defaults to top frame.
revisionNoReject if the DOM revision differs from the snapshot.
selectorNoCSS selector. Must identify exactly one element.
directionNo
documentIdNoReject the action if this snapshot document has changed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden and largely fails it. It never says whether scrolling triggers lazy loading or intersection observers, whether the scroll is instant or smooth, or that a failed expect condition does not undo the scroll (that only appears in the schema).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero filler, which is efficient. It is arguably too terse for a 13-parameter tool, but nothing in it is wasted or buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 13 parameters, a nested expect object, snapshot-guard semantics, no annotations, and no output schema, one sentence is far too thin. An agent cannot learn from the description how x/y interact with pages and direction, or what the rejection semantics mean in practice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is a middling 62%: tabId, ref, selector, browser, frameId, revision, documentId and expect are documented in the schema. The description adds only the unit clarification (CSS pixels) for x/y; the undocumented pages, origin, and direction parameters get no explanation, so it adds marginal value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ("Scroll") and resource ("the page or an element") plus the unit ("CSS pixels"), which is enough to distinguish it from siblings like browser_click or browser_move. It stops short of naming any sibling or stating a boundary case, so a 4 rather than a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this versus alternatives such as browser_move, browser_press (Page Down), or browser_click on an anchor. It also omits prerequisites implied by the schema, namely that ref requires a fresh snapshot and that revision/documentId guard against stale documents.

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