Build
Web Tools
Search current web results, then fetch full pages as clean Markdown.
Last updated
Usage-based pricing
Every call to web_search or web_read_page adds one run to billing. A base run that makes two web-tool calls counts as three runs.
web_search
+1 run per callSearch the web for current information
How it works
web_search returns relevant titles, URLs, and content snippets. Results can be targeted by country and can include recent news articles.
agents/researcher.yaml
version: "1.0"
name: researcher
model: openai/gpt-4o
description: "Research agent with web search"
system_prompt: |
You are a research assistant with web search capabilities.
Search the web to find current information and cite sources.
tools:
- web_searchParameters
| Parameter | Type | Default | Description |
|---|---|---|---|
| query | string | required | Search query |
| max_results | int | 5 | Number of results, up to 10 |
| country | string | None | ISO 3166-1 alpha-2 country code, such as DE, US, or FR |
| include_news | bool | false | Also search recent news and merge it into the results list |
Return value
Returns a results list. Each result contains:
title— page titleurl— page URLcontent— page-content snippet
web_read_page
+1 run per callFetch a page and return its content as Markdown
How it works
web_read_page fetches a web page and converts its full content to clean Markdown. Use it after web_search when the agent needs more than a search snippet.
agents/reader.yaml
version: "1.0"
name: reader
model: openai/gpt-4o
description: "Agent that reads and summarizes web pages"
system_prompt: |
You can fetch web pages and summarize their content.
Use web_search to find pages, then web_read_page to read them.
tools:
- web_search
- web_read_pageParameters
| Parameter | Type | Default | Description |
|---|---|---|---|
| url | string | required | Page URL to fetch |
| follow_redirects | boolean | true | Follow redirects and read the final page. When false, a redirect returns an error and the target in redirect_url. |
Return value
Returns a dictionary containing:
markdown— converted page contenturl— final fetched URL after redirectserror— included only on timeout, fetch failure, or blocked redirectredirect_url— target returned when a redirect is blocked