inspect_element
Reads the full content of a single UI element by path, such as a document, table, long list, or edit field, so agents can extract large text without numbering every row.
Instructions
Read the full content of one element, identified by a path.
Call get_ui_tree first, then pass the path of the element you care about
(for example "0.4.0.1"). Use this for elements that hold a lot of content -
a document, a table, a long list, an edit field - where numbering every row
would waste the whole mark budget.
Returns the element's type, name, screen rect, its value or text (up to
max_chars), and a summary of its immediate children. That child summary is
usually enough to understand a table without capturing or marking it.
Paths are positional: if the UI changed between calls, call get_ui_tree
again. Read-only.
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": {
"window": "<window>",
"path": "<path>"
},
"name": "inspect_element"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| window | Yes | ||
| max_chars | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |