Ask a question about a web page
web_ask_runAsk a natural-language question about a specific web page and receive an LLM-generated answer, so you can extract needed facts without reading the full page.
Instructions
Ask a natural-language question about a specific web page and get an LLM-generated answer. Requires url and q. Put the question in q, e.g. {"url":"https://example.com","q":"What does this company sell?"}.
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": {
"url": "<url>",
"q": "<q>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "web_ask_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Required. Natural-language question to answer about the page content. | |
| url | Yes | Required. Web page URL to fetch. | |
| proxy | No | Most expensive proxy tier to use. The page is tried on `datacenter` first and moves up only if it is blocked, stopping at this tier. Default: every tier (`mobile`). | |
| 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. | |
| maxCredits | No | Most credits this call may cost (1–25). One credit covers loading a typical page and the model reading roughly 1,500 words of it (less in languages such as Japanese); long pages are answered from their first part (`truncated: true`) unless you raise this. Charged only for what the call uses. | |
| 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. |