fix: update fetch_webpage docstring to reflect actual implementation (#6503)

The docstring incorrectly stated that fetch_webpage uses Jina AI reader.
Updated to accurately describe the actual implementation which uses:
1. Exa API (if EXA_API_KEY is available)
2. Trafilatura (fallback)
3. Readability + html2text (final fallback)

🐾 Generated with [Letta Code](https://letta.com)

Co-authored-by: Letta <noreply@letta.com>

letta/functions/function_sets/builtin.py

@@ -67,7 +67,7 @@ async def web_search(
 
 async def fetch_webpage(url: str) -> str:
     """
-    Fetch a webpage and convert it to markdown/text format using Jina AI reader.
+    Fetch a webpage and convert it to markdown/text format using Exa API (if available) or trafilatura/readability.
 
     Args:
         url: The URL of the webpage to fetch and convert

letta/services/tool_executor/builtin_tool_executor.py

@@ -311,7 +311,7 @@ class LettaBuiltinToolExecutor(ToolExecutor):
 
     async def fetch_webpage(self, agent_state: "AgentState", url: str) -> str:
         """
-        Fetch a webpage and convert it to markdown/text format using trafilatura with readability fallback.
+        Fetch a webpage and convert it to markdown/text format using Exa API (if available) or trafilatura/readability.
 
         Args:
             url: The URL of the webpage to fetch and convert