search
Run a single web query and get ranked results with title, URL, and snippet. Filter by language, news topic, time window, or domain; request per-result highlights or full page content.
Instructions
Search the live web and return ranked results (title, url, snippet) — fast, fresh, real-time web search for one focused lookup. Set topic to news for news-focused results. Pass highlight to get a ranked snippet per result, or full_content to pull the cleaned page body inline (heavier — costs more context). Narrow with domain / text include-exclude filters, a language filter (ISO 639-1 codes), and a time window (published/crawled start_time/end_time, or a relative time_range). Set include_images / include_videos to return media URLs per result.
USE FOR a single focused lookup: one fact, one entity, one document. If the question spans several independent subtopics, load and use broad_search instead — a sequence of search calls is slower and gives worse coverage than one fan-out. To read a page you already have the URL for, use extract.
keywords: web search, search the web, look up, find, check, fact, current information, latest, news, source, url, real-time
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). Defaults to 30s if unset. | |
| 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. | |
| 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. |