Hand a brief to the Berrys agent
playground_brief_startStart the Berrys agent on a brief and return at once with runId and canvasUrl; it never waits. Follow it with playground_run_events (afterSeq, optionally waitSeconds) for progress, approvals and the final response, and playground_run_diagnose if it fails. projectId defaults to the project the user has open (playground_context_current). files are node IDs of uploaded media to use as references; connectorAccountIds lets the agent read connected sources (needs connector:read). Pass conversationId to continue an earlier brief. Requires agent:start; paid steps still need approval.
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": {
"message": "<message>"
},
"name": "playground_brief_start"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | Reference file attachments to include with the brief. | |
| message | Yes | User’s creative brief or steering instructions for the current run. | |
| projectId | No | ID of the Playground project chosen for this task; obtain it from project creation, an explicit project link or current context. | |
| conversationId | No | Conversation ID for filtering or continuing the associated agent work. | |
| connectorAccountIds | No | Connected account IDs (playground_connected_sources_list) the agent may read for this brief. Only include accounts the user selected for this brief. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| next | Yes | Suggested next action; it does not authorize spending. | |
| runId | Yes | ||
| status | Yes | ||
| canvasUrl | Yes | ||
| projectId | Yes | ||
| nextAfterSeq | Yes | ||
| conversationId | Yes | ||
| retry_after_seconds | Yes |