call
Destructive
Execute an admitted tool through the runtime gateway after checking its current schema and authorization. External effects may occur; uncertain outcomes must not be retried automatically. Use when you have chosen a listing and want this gateway to run one of its admitted tools. Example arguments: {"resource_id": 133020, "tool": "get_country_profile", "arguments": {"country_code": "US"}}
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | The task query (optional; used to find immediate alternatives if execution fails) | |
| tool | Yes | The specific tool name to execute | |
| payment | No | Optional payment details (tx_hash, signature, headers) for paid endpoints | |
| arguments | No | Key-value arguments to pass to the tool | |
| account_id | No | Optional credit account ID for paid tools (defaults to your visitor ID) | |
| resource_id | Yes | The resource_id of the agent, MCP server, or API to call | |
| visitor_token | No | Your visitor token (vt_…) so I remember you. Omit on first contact. | |
| idempotency_key | No | Stable caller key for supported ticketed delivery while its execution record is retained. Reuse with identical input; uncertain execution stays paused for review. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | No | ||
| text | Yes | ||
| intent | No | ||
| status | No | ||
| visitor | No | ||
| execution | No | ||
| recommendations | No |