Snapshot page
browser_snapshotCapture visible page text and semantic interactive elements with short-lived refs. Use each ref with browser_act, then capture a fresh view after every action.
Instructions
Read visible page text plus semantic interactive elements with short-lived refs. Use a ref with browser_act, then take a fresh snapshot after every action.
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": {
"tabId": "<tabId>"
},
"name": "browser_snapshot"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | Yes | ||
| browser | No | Which connected Chrome to use: an instanceId or label from browser_list_instances. Required when more than one browser is connected; session-based tools infer it from their sessionId. | |
| maxChars | No |