docs: downgrade native tool calling to grouped item in release notes

Author: hannesrudolph

docs/update-notes/v3.33.1.mdx

@@ -14,16 +14,9 @@ This release introduces native tool calling support for OpenAI-compatible provid
 
 <img src="/img/v3.33.1/v3.33.1.png" alt="Roo Code v3.33.1 Release" width="600" />
 
-## Major Features
+## Provider Updates
 
-### Native Tool Calling for OpenAI-compatible Providers
-
-We've enabled native tool calling for providers using the OpenAI-compatible interface (thanks mrubens!) ([#9369](https://github.com/RooCodeInc/Roo-Code/pull/9369)):
-
-- **Broad Compatibility**: Enables native tool use with a wider range of models and providers that support the OpenAI format.
-- **Improved Reliability**: Offers more robust tool interactions in both streaming and non-streaming modes compared to XML-based calling.
-
-> **📚 Documentation**: See [OpenAI Compatible Provider](/providers/openai-compatible) for configuration details.
+- **Native Tool Calling for OpenAI-compatible Providers**: Enables native tool use with a wider range of models and providers that support the OpenAI format, offering more robust tool interactions in both streaming and non-streaming modes (thanks mrubens!) ([#9369](https://github.com/RooCodeInc/Roo-Code/pull/9369))
 
 ## Bug Fixes
 

docs/update-notes/v3.33.mdx

@@ -27,15 +27,10 @@ Roo Code now supports Google’s Gemini 3 Pro Preview model through direct Gemin
 - **Reliable tool usage**: Executes complex multi-step tool workflows without getting stuck or losing track, especially in long, tool-heavy tasks.
 - **Better out-of-the-box defaults**: Uses `gemini-2.5-pro` by default where supported, sets a more natural temperature of 1, cleans up the Gemini model list, and includes reasoning / “thought” tokens in cost reporting so usage numbers better match provider billing.
 
-### Native Tool Calling for OpenAI-compatible Providers
-
-We've enabled native tool calling for providers using the OpenAI-compatible interface (thanks mrubens!) ([#9369](https://github.com/RooCodeInc/Roo-Code/pull/9369)):
-
-- **Broad Compatibility**: Enables native tool use with a wider range of models and providers that support the OpenAI format.
-- **Improved Reliability**: Offers more robust tool interactions in both streaming and non-streaming modes compared to XML-based calling.
-
 ## QOL Improvements
 
+- **Native Tool Calling for OpenAI-compatible Providers** ([#9369](https://github.com/RooCodeInc/Roo-Code/pull/9369)): Enables native tool use with a wider range of models and providers that support the OpenAI format, offering more robust tool interactions in both streaming and non-streaming modes (thanks mrubens!).
+
 - **Git status in environment details** ([#9310](https://github.com/RooCodeInc/Roo-Code/pull/9310)): Shows git status information in environment details so agents have more context about untracked, modified, and staged files.
 - **Tool protocol selector in advanced settings** ([#9324](https://github.com/RooCodeInc/Roo-Code/pull/9324)): Lets you choose which tool protocol to use (such as XML vs native) without editing config files.
 - **Dynamic tool protocol resolution** ([#9286](https://github.com/RooCodeInc/Roo-Code/pull/9286)): Resolves the active tool protocol using a clear precedence hierarchy.