Skip to main content
Glama
frsorrentino

Chrome Bridge

by frsorrentino
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

scroll

Move a tab's viewport to coordinates or an element, or repeatedly advance until an element appears, network goes idle, or no new content loads for infinite feeds.

Instructions

Scroll. action=to: once to element/coordinates; action=until: repeatedly until element visible, network idle, or no new content (infinite scroll). It moves the tab's scroll position and returns it (to) or stopped_reason and steps (until); full_page_screenshot scrolls by itself, wait_for waits without scrolling.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoAbsolute horizontal position in px (action=to, without selector)
yNoAbsolute vertical position in px (action=to, without selector)
untilNono_new_content stops when the page height stops growingno_new_content
actionNoto jumps to a position or element; until scrolls repeatedly to load moreto
tab_idNoTarget tab; omitted = last tab navigated in this session, else the active one
step_pxNopx per step, default viewport height
behaviorNoinstant avoids waiting for smooth-scroll animationsauto
frame_idNoTarget iframe id from get_frames; omitted = main frame
offset_yNopx offset for fixed headers (to)
selectorNoTarget (to) or stop element (until=element)
containerNountil: selector that scrolls; default the document, or the largest scrollable element if the document does not scroll
settle_msNoPause ms after each step
max_scrollsNoCap on scroll steps, so an infinite feed terminates

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.28.0
    • addedInput schema / properties / container
      Added value: +{
+  "description": "until: selector that scrolls; default the document, or the largest scrollable element if the document does not scroll",
+  "type": "string"
+}
  2. Changed8 schema fields changedv1.10.0
    • addedInput schema / properties / action / description
      Added value: +"to jumps to a position or element; until scrolls repeatedly to load more"
    • addedInput schema / properties / behavior / description
      Added value: +"instant avoids waiting for smooth-scroll animations"
    • changedInput schema / properties / frame_id / description
      Previous value: -"action=to only"New value: +"Target iframe id from get_frames; omitted = main frame"
    • addedInput schema / properties / max_scrolls / description
      Added value: +"Cap on scroll steps, so an infinite feed terminates"
    • addedInput schema / properties / tab_id / description
      Added value: +"Target tab; omitted = last tab navigated in this session, else the active one"
    • addedInput schema / properties / until / description
      Added value: +"no_new_content stops when the page height stops growing"
    • addedInput schema / properties / x / description
      Added value: +"Absolute horizontal position in px (action=to, without selector)"
    • addedInput schema / properties / y / description
      Added value: +"Absolute vertical position in px (action=to, without selector)"
  3. First observedv1.8.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare the mutation/non-idempotent profile; the description goes further by disclosing the return shape per mode (scroll position for 'to'; stopped_reason and steps for 'until') and termination behavior (no_new_content stops when page height stops growing). No output schema exists, so this return information is valuable, though it isn't exhaustive about all 13 params.

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?

Front-loaded with a one-word purpose then dense semicolon-delimited clauses. Every clause carries mode/return/routing information, but the single long sentence is slightly crammed.

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?

For a 13-parameter tool with minimal annotations and no output schema, it covers the important call-shaping decisions (mode choice, stop conditions, return values, sibling alternatives). It omits secondary params (tab_id, frame_id, container, settle_ms, max_scrolls), which the schema handles, so it is nearly complete but not exhaustive.

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 description coverage is 100% and the schema itself already ties parameters to actions (e.g., x/y 'action=to, without selector', selector 'to or stop element (until=element)'). The description largely restates these action/parameter mappings rather than adding new syntax or format detail, so the baseline 3 applies.

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

Purpose5/5

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

States a specific verb and resource ('scroll', 'the tab's scroll position') and cleanly separates its two modes: action=to jumps once to an element/coordinates, action=until scrolls repeatedly. It also names siblings it is not (full_page_screenshot, wait_for), so an agent can route without opening schemas.

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

Usage Guidelines5/5

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

Explicit mode-selection guidance: 'to' for a single jump, 'until' for infinite-scroll loading with three named stop conditions. It also carves out alternatives by noting full_page_screenshot scrolls by itself and wait_for waits without scrolling, giving clear when-not-to-use signals.

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

Deploy Server

Other Tools