Skip to main content
Glama

tab_scroll

Scrolls a browser page or scrollable element with the real mouse wheel in a chosen direction, then returns the visible content in tab_read format.

Instructions

Scroll a page in the user's browser with the real mouse wheel, over the middle of the page or over an element, and return what is on screen afterwards, in the tab_read format.

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": {
      "direction": "<direction>"
    },
    "name": "tab_scroll"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoRef of a scrollable area from tab_read to scroll inside it. Defaults to the middle of the page.
pagesNoHow far, in screens; each is 80% of the viewport height, so some content stays. Defaults to 1.
tabIdNoTab id from tab_list or tab_read. Defaults to the active tab of the browser window the user used last.
directionYesWhich way to scroll.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does reasonably well: it discloses the physical mechanism ('real mouse wheel'), that the result is returned as post-scroll screen state in tab_read format, and the side effect of acting on the last-used browser window. It omits whether it waits for lazy-loaded content or whether scrolling is animated, so it is not exhaustive.

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

Conciseness5/5

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

A single front-loaded sentence with the action, mechanism, targeting, and output in that order, and no redundant or filler wording.

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

Completeness4/5

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

Four parameters, one required, fully documented in schema, and the description covers targeting, scope, and output shape even though there is no output schema. Minor gaps remain around timing and whether content loading is awaited.

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 100%, so every parameter is already documented, and the description largely echoes that (element vs middle of page). The return-format note adds context but no new syntax or format detail for direction, pages, or tabId, so the baseline of 3 applies.

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?

States a specific verb and resource: scroll a page in the user's browser, and adds mechanism (real mouse wheel) plus targeting (middle of page or an element). The phrase 'in the user's browser' implicitly separates it from macos_mouse_scroll, but no sibling is named, so the differentiation is left to inference.

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

Usage Guidelines3/5

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

Usage is only implied through defaults: 'ref ... Defaults to the middle of the page' and 'Defaults to the active tab of the browser window the user used last.' There is no statement of when to prefer this over macos_mouse_scroll or when a scroll is inappropriate, so an agent must infer the conditions.

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