web_search
Query multiple web search engines and receive fused, deduplicated results for research or fact-checking.
Instructions
Search the web across multiple engines and return ranked, deduplicated results.
Use this when the user wants to look something up online, find current information,
research a topic, or check a claim against live sources. Results are fused across
engines (provenance-aware rank fusion) and deduplicated. Each result carries a
human-readable handle; after you web_fetch its URL you can web_open that
handle to page through the document.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query, e.g. "rust ownership model" or "site:nature.com crispr". | |
| max_results | No | How many results to return (default 8). Raise for research, lower for a quick lookup. | |
| detail | No | "concise" (default) omits per-result engines and score to save tokens; "detailed" includes them. | concise |
| engines | No | Engine names to query (e.g. ["searxng", "ddgs"]); omit for all configured. | |
| country | No | ISO 3166-1 alpha-2 country code (e.g. "us"); omit for engine default. | |
| language | No | ISO 639-1 language code (e.g. "en"); omit for engine default. | |
| freshness | No | One of "any", "day", "week", "month", "year" (best-effort recency). | any |
| safesearch | No | One of "off", "moderate", "strict". | moderate |
| site | No | Restrict to a single host (e.g. "docs.python.org"). | |
| offset | No | Advanced result offset. Best-effort only: the keyless backends do not page reliably, so to get different results prefer refining the query. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||