Skip to main content
Glama
munimtechnologies

Computer Use

by munimtechnologies
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Scroll

scroll

Move the view up, down, left, or right by lines to bring off-screen content into view before inspecting or capturing the app state. It only moves content; nothing is clicked or selected.

Instructions

Scroll up, down, left or right by a number of lines, over element_id when given so the right pane scrolls. Use it to bring off-screen content into view before get_app_state or screenshot. It only scrolls; nothing is clicked or selected. On macOS it scrolls the target app in the background without moving the user's pointer. On Windows and Linux, without element_id it scrolls whatever is under the user's pointer, and an element with no background route gets the real pointer moved onto it (the result then says via cursor).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoScreen x to scroll over. Remote control only: the pointer moves there first. Ignored otherwise.
yNoScreen y to scroll over. Remote control only: the pointer moves there first. Ignored otherwise.
amountNoNumber of scroll lines, 1 to 100 (default 5)
directionNoScroll direction (default down)
element_idNoElement to scroll, from get_app_state; the nearest scrollable area around it moves. Omit to scroll the last inspected app (macOS) or whatever is under the pointer (Windows, Linux).
state_queryNoWith return_state, list only elements whose role, label or value contains this text, like get_app_state's query
return_stateNoAfter acting, wait briefly for the UI to settle and append a fresh get_app_state of the app you last read, so you can check the result and pick the next target in the same call. Its ids replace every earlier id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.2
    • addedInput schema / properties / return_state
      Added value: +{
+  "description": "After acting, wait briefly for the UI to settle and append a fresh get_app_state of the app you last read, so you can check the result and pick the next target in the same call. Its ids replace every earlier id.",
+  "type": "boolean"
+}
    • addedInput schema / properties / state_query
      Added value: +{
+  "description": "With return_state, list only elements whose role, label or value contains this text, like get_app_state's query",
+  "type": "string"
+}
  2. Changed2 schema fields changedv0.4.2
    • addedInput schema / properties / x
      Added value: +{
+  "description": "Screen x to scroll over. Remote control only: the pointer moves there first. Ignored otherwise.",
+  "type": "number"
+}
    • addedInput schema / properties / y
      Added value: +{
+  "description": "Screen y to scroll over. Remote control only: the pointer moves there first. Ignored otherwise.",
+  "type": "number"
+}
  3. Changed2 schema fields changedv0.4.0
    • changedInput schema / properties / amount / description
      Previous value: -"Number of scroll lines (default 5)"New value: +"Number of scroll lines, 1 to 100 (default 5)"
    • changedInput schema / properties / element_id / description
      Previous value: -"Element to position the pointer over before scrolling, from get_app_state. Omit to scroll at the current pointer position."New value: +"Element to scroll, from get_app_state; the nearest scrollable area around it moves. Omit to scroll the last inspected app (macOS) or whatever is under the pointer (Windows, Linux)."
  4. Changed3 schema fields changedv0.3.1
    • changedInput schema / properties / amount / description
      Previous value: -"Scroll lines (default 5)"New value: +"Number of scroll lines (default 5)"
    • addedInput schema / properties / direction / description
      Added value: +"Scroll direction (default down)"
    • addedInput schema / properties / element_id / description
      Added value: +"Element to position the pointer over before scrolling, from get_app_state. Omit to scroll at the current pointer position."
  5. First observedv0.3.0

TDQS

A4.5/5.0
Behavior5/5

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

With annotations only covering safety flags, the description carries the real behavioral burden and does so: platform-specific side effects (macOS scrolls the target app in the background without moving the pointer; Windows/Linux scroll under the pointer or move the real pointer onto elementless targets), plus the 'via cursor' result marker. This is exactly the side-effect disclosure an agent needs for a non-read-only tool.

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 then usage and side effects; no filler. The final platform sentence is dense but every clause is load-bearing for correct invocation.

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 7-parameter, no-output-schema tool with platform-dependent behavior, the description covers the action, usage, and cross-platform side effects well. It leaves return_state/state_query semantics entirely to the schema, which is acceptable, but a note on what the scroll call returns by default would close the remaining gap.

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 the schema already documents every parameter, including element_id fallback behavior and the x/y remote-control caveat. The description's parameter mentions (element_id 'so the right pane scrolls', x/y platform behavior) largely restate the schema rather than adding new syntax or constraints, so 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 (scroll) plus resource/axis and line count, and names the targeting parameter (element_id) that selects which pane moves. An agent can tell this apart from click, drag, and hover siblings immediately.

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?

Explicitly states when to use it (bring off-screen content into view before get_app_state or screenshot) and draws a hard boundary against alternatives ('It only scrolls; nothing is clicked or selected'). This is direct routing guidance rather than implied usage.

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