diff --git a/agent/templates/DB Assistant.json b/agent/templates/DB Assistant.json
index 5be936d05..bbb1b40ca 100644
--- a/agent/templates/DB Assistant.json	
+++ b/agent/templates/DB Assistant.json	
@@ -1,7 +1,7 @@
 {
   "id": 6,
   "title": "DB Assistant",
-  "description": "Database query assistant. It converts questions into SQL statements and queries them in the database. You need to provide 3 kinds of knowledge base: 1. DDL data in the database. 2. Sample text questions converted to SQL statements. 3. A description of the database contents, including but not limited to: tables, records, and so on. You will also need to set up database configuration information: like IP Port ...",
+  "description": "A more advanced agent that converts user queries into SQL statements, executes the queries, and assesses and returns the results. You must prepare three knowledge bases: 1: DDL for your database; 2: Examples of user queries converted to SQL statements; 3: A comprehensive description of your database, including but not limited to tables and records. And you are also required to configure the corresponding database.",
   "canvas_type": "chatbot",
   "dsl": {
             "answer": [],
diff --git a/agent/templates/HR_callout_zh.json b/agent/templates/HR_callout_zh.json
index fa8d1ed11..aec747252 100644
--- a/agent/templates/HR_callout_zh.json
+++ b/agent/templates/HR_callout_zh.json
@@ -1,7 +1,7 @@
 {
   "id": 2,
-  "title": "HR call-out assistant(Chinese)",
-  "description": "A HR call-out assistant. It will introduce the given job, answer the candidates' question about this job. And the most important thing is that it will try to obtain the contact information of the candidates. What you need to do is to link a knowledgebase which contains job description in 'Retrieval' component.",
+  "title": "HR recruitment pitch assistant (Chinese)",
+  "description": "A recruitment pitch assistant capable of pitching a candidate, presenting a job opportunity, addressing queries, and requesting the candidate's contact details. Let's begin by linking a knowledge base containing the job description in 'Retrieval'!",
   "canvas_type": "chatbot",
   "dsl": {
     "answer": [],
diff --git a/agent/templates/customer_service.json b/agent/templates/customer_service.json
index 46c79d5cb..9f4a810a3 100644
--- a/agent/templates/customer_service.json
+++ b/agent/templates/customer_service.json
@@ -1,7 +1,7 @@
 {
   "id": 3,
   "title": "Customer service",
-  "description": "A call-in customer service chat bot. It will provide useful information about the products, answer customers' questions and soothe the customers' bad emotions.",
+  "description": "A customer service chatbot that explains product specifications, addresses customer queries, and alleviates negative emotions.",
   "canvas_type": "chatbot",
   "dsl": {
     "answer": [],
diff --git a/agent/templates/general_chat_bot.json b/agent/templates/general_chat_bot.json
index a1c21b5ae..0369658fc 100644
--- a/agent/templates/general_chat_bot.json
+++ b/agent/templates/general_chat_bot.json
@@ -1,7 +1,7 @@
 {
   "id": 1,
-  "title": "Chat bot",
-  "description": "A general chat bot. It is based on Self-RAG mechanism. What you need to do is setting up knowleage base in 'Retrieval'",
+  "title": "General-purpose chatbot",
+  "description": "A general-purpose chatbot based on Self-RAG. Let's begin by setting up your knowledge base in 'Retrieval'!",
   "canvas_type": "chatbot",
   "dsl": {
     "answer": [],
diff --git a/agent/templates/interpreter.json b/agent/templates/interpreter.json
index 8f08c59b3..2c31c0580 100644
--- a/agent/templates/interpreter.json
+++ b/agent/templates/interpreter.json
@@ -1,7 +1,7 @@
 {
   "id": 4,
   "title": "Interpreter",
-  "description": "An interpreter. Type the content you want to translate and the object language like: Hi there => Spanish. Hava a try!",
+  "description": "A simple interpreter that translates user input into a target language. Try 'Hi there => Spanish' to see the translation!",
   "canvas_type": "chatbot",
   "dsl": {
     "answer": [],
diff --git a/agent/templates/text2sql.json b/agent/templates/text2sql.json
index ca1787c0f..4dc3232ef 100644
--- a/agent/templates/text2sql.json
+++ b/agent/templates/text2sql.json
@@ -1,7 +1,7 @@
 {
   "id": 5,
   "title": "Text To SQL",
-  "description": "An agent tool provides the ability to convert text questions into SQL statements, you will need to provide 3 kinds of knowledge bases. 1. DDL data for the database. 2. Examples of text questions converted into SQL statements. 3. A description of the database contents, including but not limited to: tables, records, etc...  ",
+  "description": "An agent that converts user queries into SQL statements. You must prepare three knowledge bases: 1: DDL for your database; 2: Examples of user queries converted to SQL statements; 3: A comprehensive description of your database, including but not limited to tables and records.",
   "canvas_type": "chatbot",
   "dsl": {
             "answer": [],
diff --git a/agent/templates/websearch_assistant.json b/agent/templates/websearch_assistant.json
index 4ec9382f5..a6b2b86c5 100644
--- a/agent/templates/websearch_assistant.json
+++ b/agent/templates/websearch_assistant.json
@@ -1,7 +1,7 @@
 {
   "id": 0,
   "title": "WebSearch Assistant",
-  "description": "A chat assistant that combines information both from knowledge base and web search engines. It integrates information from the knowledge base and relevant search engines to answer a given question. What you need to do is setting up knowleage base in 'Retrieval'.",
+  "description": "A chat assistant template that integrates information extracted from a knowledge base and web searches to respond to queries. Let's begin by setting up your knowledge base in 'Retrieval'!",
   "canvas_type": "chatbot",
   "dsl": {
     "answer": [],