Skip to main content
Glama

iphone_scroll

Scroll the screen center in a direction to reach items outside visible lists, pages, or carousels, then inspect the updated UI tree; use exact swipes for precise drags.

Instructions

Scroll the content in the middle of the screen in a direction.

Use it to reach items outside the visible area of lists, pages and carousels, then call iphone_ui_tree
again. It starts in the screen center, so it never triggers system edge gestures; for exact drags use
iphone_swipe.

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": "iphone_scroll"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountNoDistance as a share of the screen size, 0.1–0.9.
directionYesWhere to move the view: 'down' reveals content further down (finger moves up), 'right' reveals content to the right.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.2.0
    • addedInput schema / properties / amount / description
      Added value: +"Distance as a share of the screen size, 0.1–0.9."
    • addedInput schema / properties / amount / maximum
      Added value: +0.9
    • addedInput schema / properties / amount / minimum
      Added value: +0.1
    • addedInput schema / properties / direction / description
      Added value: +"Where to move the view: 'down' reveals content further down (finger moves up), 'right' reveals content to the right."
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses that scrolling always begins at the screen center and therefore never triggers system edge gestures, and that a UI-tree re-read is the intended follow-up. That is meaningful operational context not encoded in the annotations, though it does not say how much or how fast a given scroll moves content.

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?

Two tight sentences: the action and its locus come first, then the routing constraint, then the alternative. Every clause carries distinct information with no repetition of schema or annotation content.

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 simple two-parameter tool with full schema coverage and an output schema, the description covers purpose, when to use it, the required follow-up, and the edge-gesture safety constraint. The only minor gap is the absence of any note on scroll settling or timing before reading the UI tree.

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% and the schema already explains the direction-to-content mapping and the 0.1–0.9 amount range, so the description adds no parameter detail beyond it. Baseline 3 applies when the schema does the heavy lifting; the description's 'starts in the screen center' hints at behavior rather than parameter meaning.

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 (scroll) plus the resource and its scope ('the content in the middle of the screen') and explicitly distinguishes itself from the sibling iphone_swipe, which is for exact drags. An agent can select it without opening the schema.

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?

Gives an explicit trigger ('use it to reach items outside the visible area of lists, pages and carousels'), a follow-up step ('then call iphone_ui_tree again'), and names the alternative (iphone_swipe) with the condition that selects it. When-to-use and when-not-to-use are both covered.

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