chore(tools/fetch,web_fetch,web_search): improve tool descriptions

Christian Rocha created

Change summary

internal/agent/tools/fetch.md      | 2 +-
internal/agent/tools/web_fetch.md  | 2 +-
internal/agent/tools/web_search.md | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)

Detailed changes

internal/agent/tools/fetch.md 🔗 

@@ -1,4 +1,4 @@
-Fetches raw content from URL and returns it in specified format without any AI processing.
+Fetch raw content from a URL as text, markdown, or html (max 5MB); no AI processing. For analysis or extraction use agentic_fetch.
 
 <when_to_use>
 Use this tool when you need:

internal/agent/tools/web_fetch.md 🔗 

@@ -1,4 +1,4 @@
-Fetches content from a web URL (for use by sub-agents).
+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.
 
 <usage>
 - Provide a URL to fetch

internal/agent/tools/web_search.md 🔗 

@@ -1,4 +1,4 @@
-Searches the web using DuckDuckGo and returns search results.
+Search the web via DuckDuckGo; returns titles, URLs, and snippets. Follow up with web_fetch to get full page content.
 
 <usage>
 - Provide a search query to find information on the web