Skip to main content
Glama

desktop_scroll

Destructive

Scroll with the mouse wheel at a point of a desktop session: dy > 0 scrolls down, dy < 0 up, in wheel notches (at most 20). The user started this desktop session for you in Termalin and can watch it. Coordinates are pixels of your last desktop_screenshot. Never type passwords, keys or other secrets: when a sign-in or secret is needed, stop and ask the user to type it themselves.

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": {
      "session_id": "<session_id>",
      "x": "<x>",
      "y": "<y>",
      "dy": "<dy>"
    },
    "name": "desktop_scroll"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesHorizontal position, in pixels of the last desktop_screenshot
yYesVertical position, in pixels of the last desktop_screenshot
dxNoHorizontal notches; positive scrolls right (optional)
dyYesWheel notches; positive scrolls down
session_idYesDesktop session id from desktop_list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare openWorldHint, destructiveHint, and non-idempotence; the description adds context the annotations cannot: the user is watching the live session in Termalin, coordinates are tied to the last screenshot, and there is a hard cap of 20 notches per call. It does not explain why a scroll is flagged destructive (page state changes or accidental triggers) or what a failed scroll returns.

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?

Three sentences, front-loaded with the action and the sign convention, followed by coordinate frame and safety policy. Every sentence carries usable information, though the secret-handling warning is longer than the scroll mechanics it accompanies.

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 five-parameter, no-output-schema input tool with full annotation coverage, the description supplies what the structured fields cannot: coordinate provenance, the per-call notch ceiling, session observability, and secret-handling policy. Remaining gaps (error behavior, whether the session must be active) are minor for a scroll action.

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 x, y, dx, dy and session_id are already documented; the description mostly restates the dy sign convention that the schema also gives. Its one genuine addition is the 'at most 20' notch limit, which the schema does not encode, and it omits any mention of the optional dx parameter. Baseline 3 is appropriate.

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?

Names a specific verb and resource ('Scroll with the mouse wheel at a point of a desktop session') and pins the coordinate frame to the last desktop_screenshot, which separates it cleanly from desktop_click/desktop_move siblings that act on the same coordinates.

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

Usage Guidelines4/5

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

Explains the dy sign convention, the notch magnitude cap (at most 20), and the coordinate reference, plus an explicit stop-and-ask rule when a sign-in or secret is required. It stops short of routing to alternatives (e.g., use desktop_click to click, desktop_key to type) after a scroll moves content.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.