Web research (search + read)
web_researchWeb search PLUS the cleaned text of the top pages in one call (pages are fetched in parallel). Prefer this over web_search + web_fetch whenever you need to read the results, not just list them.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query | |
| num | No | Pages to read (default 3) | |
| entity | No | Explicit entity for official_website candidate identification; ownership is not verified. | |
| intent | No | ||
| max_chars | No | Characters per page (default 2500) | |
| max_units | No | ||
| idempotency_key | No | Reuse for a retry of exactly the same operation/input. | |
| max_duration_ms | No |