git.iko.soy/crush
on main help sign in
chore(tools/fetch,web_fetch,web_search): improve tool descriptions
d4cf8a0Christian Rocha
internal/agent/tools/fetch.md+1−1
compare with main
unifiedsplit
@@ -1,4 +1,4 @@
1−Fetches raw content from URL and returns it in specified format without any AI processing.
1+Fetch raw content from a URL as text, markdown, or html (max 5MB); no AI processing. For analysis or extraction use agentic_fetch.
2
2
3<when_to_use>
3<when_to_use>
4Use this tool when you need:
4Use this tool when you need:
internal/agent/tools/web_fetch.md+1−1
@@ -1,4 +1,4 @@
1−Fetches content from a web URL (for use by sub-agents).
1+Fetch a web URL and return content as markdown; for use inside sub-agents. Large pages (>50KB) are saved to a temp file for grep/view.
2
2
3<usage>
3<usage>
4- Provide a URL to fetch
4- Provide a URL to fetch
internal/agent/tools/web_search.md+1−1
@@ -1,4 +1,4 @@
1−Searches the web using DuckDuckGo and returns search results.
1+Search the web via DuckDuckGo; returns titles, URLs, and snippets. Follow up with web_fetch to get full page content.
2
2
3<usage>
3<usage>
4- Provide a search query to find information on the web
4- Provide a search query to find information on the web