Clarify doc about system prompt modification

docs/source/conceptual_guides/intro_agents.md

@@ -21,7 +21,7 @@ Any efficient system using AI will need to provide LLMs some kind of access to t
 
 In other words, give them some ***agency***. Agentic programs are the gateway to the outside world for LLMs.
 
-For a regiorous definition, AI Agents are *“programs in which the workflow is determined by LLM outputs”*.
+For a rigorous definition, AI Agents are *“programs in which the workflow is determined by LLM outputs”*.
 
 Any system leveraging LLMs will integrate the LLM outputs into code. The influence of the LLM's input on the code workflow is the level of agency of LLMs in the system.
 

docs/source/reference/agents.md

@@ -17,7 +17,7 @@ rendered properly in your Markdown viewer.
 
 <Tip warning={true}>
 
-Transformers Agents is an experimental API which is subject to change at any time. Results returned by the agents
+Smolagents is an experimental API which is subject to change at any time. Results returned by the agents
 can vary as the APIs or underlying models are prone to change.
 
 </Tip>
@@ -33,6 +33,8 @@ We provide two types of agents, based on the main [`Agent`] class.
   - [`CodeAgent`] is the default agent, it writes its tool calls in Python code.
   - [`ToolCallingAgent`] writes its tool calls in JSON.
 
+Both require arguments `model` and list of tools `tools` at initialization.
+
 
 ### Classes of agents
 

docs/source/reference/tools.md

@@ -17,7 +17,7 @@ rendered properly in your Markdown viewer.
 
 <Tip warning={true}>
 
-Transformers Agents is an experimental API which is subject to change at any time. Results returned by the agents
+Smolagents is an experimental API which is subject to change at any time. Results returned by the agents
 can vary as the APIs or underlying models are prone to change.
 
 </Tip>

docs/source/tutorials/building_good_agents.md

@@ -181,11 +181,17 @@ Put yourself in the shoes if your model: if you were the model solving the task,
 
 Would you need some added claritications ? 
 
-To provide extra information, we do not recommend modifying the system prompt compared to default : there are many adjustments there that you do not want to mess up except if you understand the prompt very well.
+To provide extra information, we do not recommend to change the system prompt right away: the default system prompt has many adjustments that you do not want to mess up except if you understand the prompt very well.
 Better ways to guide your LLM engine are:
 - If it 's about the task to solve: add all these details to the task. The task could be 100s of pages long.
 - If it's about how to use tools: the description attribute of your tools.
 
+If after trying the above, you still want to change the system prompt, your new system prompt passed to `system_prompt` upon agent initialization needs to contain the following placeholders that will be used to insert certain automatically generated descriptions when running the agent:
+- `"{{tool_descriptions}}"` to insert tool descriptions
+- `"{{managed_agents_description}}"` to insert the description for managed agents if there are any
+- For `CodeAgent` only: `"{{authorized_imports}}"` to insert the list of authorized imports.
+
+
 ### 3. Extra planning
 
 We provide a model for a supplementary planning step, that an agent can run regularly in-between normal action steps. In this step, there is no tool call, the LLM is simply asked to update a list of facts it knows and to reflect on what steps it should take next based on those facts.