diff --git a/README.md b/README.md
index 8cc9f68..cd9a764 100644
--- a/README.md
+++ b/README.md
@@ -41,33 +41,63 @@ tags:
 
 - Prompt template
 
-  - Prompt type: `llama-3-chat`
+  - Prompt type for chat: `llama-3-chat`
 
-  - Prompt string
+    - Prompt string
+  
+      ```text
+      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+  
+      {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+  
+      {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+  
+      {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+  
+      {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+      ```
 
-    ```text
-    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+  - Prompt type for tool use: `llama-3-tool`
+ 
+    - Prompt string
 
-    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+      ```text
+      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
 
-    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-
-    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
-
-    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-    ```
+      {system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>
+  
+      Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+  
+      Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+  
+      [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","unit"]}}}]
+  
+      Question: {user_message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+      ```
 
 - Context size: `128000`
 
 - Run as LlamaEdge service
 
-  ```bash
-  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
-      llama-api-server.wasm \
-      --prompt-template llama-3-chat \
-      --ctx-size 128000 \
-      --model-name Llama-3.2-3b
-  ```
+  - Chat
+  
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
+        llama-api-server.wasm \
+        --prompt-template llama-3-chat \
+        --ctx-size 128000 \
+        --model-name Llama-3.2-3b
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
+        llama-api-server.wasm \
+        --prompt-template llama-3-tool \
+        --ctx-size 128000 \
+        --model-name Llama-3.2-3b
+    ```
 
 - Run as LlamaEdge command app