diff --git a/tools/server/public_simplechat/index.html b/tools/server/public_simplechat/index.html
index c9b508eecf..3cd840569c 100644
--- a/tools/server/public_simplechat/index.html
+++ b/tools/server/public_simplechat/index.html
@@ -42,11 +42,15 @@
 
             <hr>
             <div id="tool-div">
+                <div>
                 <div class="sameline">
-                    <textarea id="toolname-in" rows="1" placeholder="name of tool to run"></textarea>
+                    <textarea id="toolname-in" class="flex-grow" rows="1" placeholder="name of tool to run"></textarea>
                     <button id="tool-btn">run tool</button>
                 </div>
+                </div>
+                <div class="sameline">
                 <textarea id="toolargs-in" class="flex-grow" rows="2" placeholder="arguments to pass to the specified tool"></textarea>
+                </div>
             </div>
 
             <hr>
diff --git a/tools/server/public_simplechat/readme.md b/tools/server/public_simplechat/readme.md
index d2a1e22df6..29214369ec 100644
--- a/tools/server/public_simplechat/readme.md
+++ b/tools/server/public_simplechat/readme.md
@@ -328,8 +328,9 @@ to the generated code directly. Either way always remember to cross check the to
 generated responses when using tool calling.
 
 May add
-* web_fetch along with a corresponding simple local proxy server logic that can bypass the
-  CORS restrictions applied if trying to directly fetch from the browser js runtime environment.
+* web_fetch along with a corresponding simple local web proxy/caching server logic that can bypass
+  the CORS restrictions applied if trying to directly fetch from the browser js runtime environment.
+  Inturn maybe with a white list of allowed sites to access or so.
 
 
 #### Extending wiht new tools
@@ -367,7 +368,7 @@ structures also.
 
 Update to use web worker.
 
-Make the Tool Call related ui elements use up horizontal space properly.
+WebFetch and Local web proxy/caching server
 
 Try and trap promises based flows to ensure all generated results or errors if any are caught
 before responding back to the ai model.