Computer Use

Overview Schema Source Related Servers Discussions Admin

Hover

hover

Idempotent

Move the agent pointer over an element or screen position without clicking to reveal menus, tooltips, toolbars, or drag handles, then capture app state or a screenshot.

Instructions

Move the agent pointer over an element or screen position without clicking, to reveal hover menus, toolbars, tooltips or drag handles. Follow with get_app_state or screenshot to see what appeared. Use click to activate. Pass element_id or x and y, not both. On macOS the user's own mouse pointer is not moved; on Windows and Linux it may be, and the result then says via cursor.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "hover"
  }
}

Input Schema

Name	Required	Description
`x`	No	Screen x coordinate in points, used together with y when no element_id is given
`y`	No	Screen y coordinate in points, used together with x when no element_id is given
`element_id`	No	Element id from the most recent get_app_state snapshot, e.g. e12
`state_query`	No	With return_state, list only elements whose role, label or value contains this text, like get_app_state's query
`return_state`	No	After acting, wait for the app to finish reacting (up to 2 s) 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.

Changed1 schema field changedv0.7.1Oct 15, 2026

changedInput schema / properties / return_state / description

Previous value: -"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."New value: +"After acting, wait for the app to finish reacting (up to 2 s) 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."

Changed2 schema fields changedv0.5.2Sep 30, 2026

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"
+}

Changed3 schema fields changedv0.3.1Sep 16, 2026

changedInput schema / properties / element_id / description

Previous value: -"Element id from get_app_state"New value: +"Element id from the most recent get_app_state snapshot, e.g. e12"

addedInput schema / properties / x / description

Added value: +"Screen x coordinate in points, used together with y when no element_id is given"

addedInput schema / properties / y / description

Added value: +"Screen y coordinate in points, used together with x when no element_id is given"

First observedv0.3.0Sep 16, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is partly covered. The description adds genuinely non-obvious behavioral context beyond the annotations: on macOS the user's pointer is not moved, on Windows/Linux it may be, and the result reports 'via cursor'. It does not discuss any notion of limits or failure modes, so not a full 5.

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?

It is a short, front-loaded block of sentences with no filler. The primary action and its purpose come first, followed by follow-up guidance, the targeting constraint, and the platform caveat, each earning its place.

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

Completeness5/5

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

There is no output schema, and the description compensates by telling the agent how to observe the result ('Follow with get_app_state or screenshot to see what appeared'). Combined with the mutual-exclusion rule and platform behavior, the description is complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all five parameters, which sets a baseline of 3. The description adds a real semantic constraint not in the schema: element_id and x/y are mutually exclusive ('not both'), which clarifies how the targeting parameters interact.

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?

The description gives a specific verb (move the agent pointer over) plus the resource (an element or screen position) and the reason (reveal hover menus, toolbars, tooltips, drag handles). It also explicitly contrasts with the sibling action by saying 'Use click to activate', so the agent can distinguish hover from click without opening either 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?

It states when to use it (to reveal hover content), what to do afterward ('Follow with get_app_state or screenshot'), and how to escalate ('Use click to activate'). It also gives the exclusivity rule for the two targeting modes ('Pass element_id or x and y, not both'), leaving nothing to inference.

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