Run a saved query now
saved_queries_runStarts a saved query run now instead of waiting for its schedule, returning the running job; check run and match lists for results.
Instructions
Start a run of a saved query now instead of waiting for its schedule. Paid: the run searches live and charges what its searches cost, up to the query's maxCreditsPerRun, when it finishes in about a minute. Answers at once with the run, still running; read saved_queries_runs_list and saved_queries_matches_list for the result. A paused, capped or broken query must be resumed first.
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": {
"id": "<id>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "saved_queries_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The saved query's id. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |