Staan web search
web_searchRead-onlyIdempotent
Search the internet and return ranked results with titles, URLs, snippets, and optional full page content, with domain and market filters.
Instructions
Search the internet. Returns ranked results as a JSON array of {"title", "url", "snippet", "full_content"?}.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query in natural language. | |
| market | No | Language-country market(s) to search: fr-fr, de-de, en-us, en-gb, en-fr, en-ca, en-au, en-in, en-ie, en-nz, en-za, en-sg. Pass one, a list, or wildcards ('en-*' for all English markets, '*' for all). Several markets are merged by rank and de-duplicated by URL; each is a separate billable request, so prefer one unless you need broader coverage. | en-gb |
| offset | No | Offset of the first result, for paging: pages hold up to 10 results, at most 40 per query. | |
| full_content | No | Page text returned with each result. Default 'none' omits it; 'markdown' adds it and makes the response very large; 'html' is much larger still. | none |
| exclude_domains | No | Drop results from these sites, e.g. ['pinterest.com']; subdomains too. At most 10. Not with include_domains. | |
| include_domains | No | Only return results from these sites, e.g. ['wikipedia.org']; subdomains match. At most 10. Not with exclude_domains. | |
| simple_response | No | false returns the raw Staan response, one entry per market, instead of the flat list. |