search
Find ranked web results and read pages to return passages answering a query, with people, places, organizations and dates resolved; unread pages list why.
Instructions
Search the web and get ranked results. Pages Flux reads come back with the passages that answer the query, with people, places, organisations and dates written in. Results it could not read are listed with the reason. Use it to find sources; use lineage to read a specific document or link you already have.
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": {
"query": "<query>"
},
"name": "search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What to search for. | |
| enrich | No | How many results to read for passages, up to max_results (default: all). 0 returns results without reading any pages, which is fastest. | |
| max_results | No | Most results to return (default 10). Out-of-range values are moved inside. | |
| allowed_domains | No | Only return pages from these sites (up to 10). | |
| blocked_domains | No | Never return pages from these sites (up to 20). |