Search the web
web_search_runSearches the public web and returns ranked organic results with snippets so agents can find relevant pages and sources; supports pagination, region, and date filters.
Instructions
Search the public web and return ranked organic results with snippets. Requires query. Returns a list (use page when paginated).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"query": "<query>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "web_search_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-based). Default: 1. | |
| query | Yes | Required. Search query text to run against the public web. | |
| region | No | ISO 3166-1 country code for localized results (e.g. US, GB, CA). | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| datePosted | No | Optional filter by when results were posted. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |