broad_search
Expands a user's full question into multiple related sub-queries and searches them concurrently to provide broad multi-angle results for comparisons, surveys, and deep research.
Instructions
Broad multi-angle web search with Octen. Best for questions that span several subtopics where a single search only reaches a few: comparisons across many sources (pricing, products, vendors), surveys and deeper research, and any multi-angle question. Pass the user's full question as query AS-IS — Octen expands it into related sub-queries and searches them concurrently, returning results grouped per sub-query (not deduplicated). Do NOT pre-split the question or call this repeatedly; raise max_queries for broader coverage instead. For a single focused lookup, use search. Per-sub-query options (count, topic, language filter, domain / text filters, time window, highlight / full_content, media) are the same as search and apply to every sub-query.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results to return (1-100). Default 5. | |
| query | Yes | Search query. Max 500 chars. | |
| topic | No | Search category: `general` for broad web search, `news` for news-focused results. Default general. | general |
| format | No | Format of returned content. Default text. | text |
| timeout | No | Request timeout in seconds (1-60). | |
| end_time | No | Upper bound for the time window, ISO 8601. | |
| language | No | Languages to filter results by, as ISO 639-1 codes. Empty = no filter. | |
| highlight | No | Return a ranked highlighted snippet per result. Omit to use the server default. | |
| safesearch | No | Adult-content filter. Default strict. | strict |
| start_time | No | Lower bound for the time window, ISO 8601 (e.g. '2025-01-01T00:00:00Z'). | |
| time_basis | No | Which timestamp the time window filters against: page `published` date, last `crawled` date, or `auto`. Default auto. | auto |
| time_range | No | Relative time window (e.g. `week`, `month`). Mutually exclusive with `start_time`/`end_time` — if both are given, the absolute range wins. | |
| max_queries | No | Upper bound on the number of sub-queries generated (1-30). Default 5 — raise toward 30 for surveys / deeper research, lower for a tighter search. | |
| exclude_text | No | Drop results whose content contains any of these strings. Max 5, each ≤30 chars. | |
| full_content | No | Return the cleaned full page body per result. Heavier than `highlight` — use only when the snippet isn't enough. Omit to use the server default (off). | |
| include_text | No | Only return results whose content contains all of these strings. Max 5, each ≤30 chars. | |
| include_images | No | Return image URLs (and a cover image) found on each result page. | |
| include_videos | No | Return video URLs found on each result page. | |
| exclude_domains | No | Drop results from these domains. Max 150, each ≤30 chars. | |
| include_domains | No | Only return results from these domains (e.g. 'arxiv.org'). Max 1000, each ≤30 chars. |