Merge pull request #1881 from crewAIInc/feat/improve-tool-docs

* Improving tool calling to pass dictionaries instead of strings

* Fix issues with parsing none/null

* remove prints and unnecessary comments

* Fix crew_test issues with function calling

* improve prompting

* add back in support for add_image

* add tests for tool validation

* revert back to figure out why tests are timing out

* Update cassette

* trying to find what is timing out

* add back in guardrails

* add back in manager delegation tests

* Trying to fix tests

* Force test to pass

* Trying to fix tests

* add in more role tests

* add back old tool validation

* updating tests

* vcr

* Fix tests

* improve function llm logic

* vcr 2

* drop llm

* Failing test

* add more tests back in

* Revert tool validation

docs/concepts/tools.mdx

@@ -150,15 +150,20 @@ There are two main ways for one to create a CrewAI tool:
 
 ```python Code
 from crewai.tools import BaseTool
+from pydantic import BaseModel, Field
 
+class MyToolInput(BaseModel):
+    """Input schema for MyCustomTool."""
+    argument: str = Field(..., description="Description of the argument.")
 
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
-    description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
+    description: str = "What this tool does. It's vital for effective utilization."
+    args_schema: Type[BaseModel] = MyToolInput
 
     def _run(self, argument: str) -> str:
-        # Implementation goes here
-        return "Result from custom tool"
+        # Your tool's logic here
+        return "Tool's result"
 ```
 
 ### Utilizing the `tool` Decorator