adl_prepare_input
Inspects a UI control at a given image point and moves the pointer onto it without clicking, returning its role, name, and focus so you can verify the target before committing an action.
Instructions
In interactive_desktop, inspect the intended control at a source-image point and move the real pointer onto it without clicking. Returns actual role/name, pointer hit and keyboard focus, plus a one-shot confirmation valid<=30s. Optional include_image returns a fresh surrounding crop. Check this observation before adl_commit_input; target, focus, geometry and human input are checked again at commit.
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>",
"frame_id": "<frame_id>",
"expected_revision": "<expected_revision>",
"action": "<action>",
"point": "<point>"
},
"name": "adl_prepare_input"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| point | Yes | ||
| action | Yes | ||
| frame_id | Yes | ||
| session_id | Yes | ||
| include_image | No | ||
| expected_target | No | ||
| expected_revision | Yes |