docs: cross link working w/ memory in tools (#4464)

docs/docs/agents/context.md

@@ -107,7 +107,7 @@ Common use cases:
         config: RunnableConfig,
     ) -> list[AnyMessage]:
         # highlight-next-line
-        user_name = config.get("configurable", {}).get("user_name")
+        user_name = config["configurable"].get("user_name")
         system_msg = f"You are a helpful assistant. User's name is {user_name}"
         return [{"role": "system", "content": system_msg}] + state["messages"]
 
@@ -162,7 +162,7 @@ Common use cases:
     })
     ```
 
-## Tools
+## Accessing Context in Tools
 
 Tools can access context through special parameter **annotations**.
 
@@ -183,7 +183,7 @@ Tools can access context through special parameter **annotations**.
     ) -> str:
         """Look up user info."""
         # highlight-next-line
-        user_id = config.get("configurable", {}).get("user_id")
+        user_id = config["configurable"].get("user_id")
         return "User is John Smith" if user_id == "user_123" else "Unknown user"
 
     agent = create_react_agent(
@@ -231,66 +231,6 @@ Tools can access context through special parameter **annotations**.
     })
     ```
 
+### Update Context from Tools
 
-## Update context from tools
-
-Tools can modify the agent's state during execution. This is useful for persisting intermediate results or making information accessible to subsequent tools or prompts.
-
-```python
-from typing import Annotated
-from langchain_core.tools import InjectedToolCallId
-from langchain_core.messages import ToolMessage
-from langgraph.prebuilt import InjectedState
-from langgraph.types import Command
-
-class CustomState(AgentState):
-    # highlight-next-line
-    user_name: str
-
-def get_user_info(
-    # highlight-next-line
-    tool_call_id: Annotated[str, InjectedToolCallId],
-    # highlight-next-line
-    config: RunnableConfig
-) -> Command:
-    """Look up user info."""
-    # highlight-next-line
-    user_id = config.get("configurable", {}).get("user_id")
-    name = "John Smith" if user_id == "user_123" else "Unknown user"
-    return Command(update={
-        # highlight-next-line
-        "user_name": name,
-        # update the message history
-        # highlight-next-line
-        "messages": [
-            ToolMessage(
-                "Successfully looked up user information",
-                # highlight-next-line
-                tool_call_id=tool_call_id
-            )
-        ]
-    })
-
-def greet(
-    # highlight-next-line
-    state: Annotated[CustomState, InjectedState]
-) -> str:
-    """Use this to greet the user once you found their info."""
-    user_name = state["user_name"]
-    return f"Hello {user_name}!"
-
-agent = create_react_agent(
-    model="anthropic:claude-3-7-sonnet-latest",
-    tools=[get_user_info, greet],
-    # highlight-next-line
-    state_schema=CustomState
-)
-
-agent.invoke(
-    {"messages": [{"role": "user", "content": "greet the user"}]},
-    # highlight-next-line
-    config={"configurable": {"user_id": "user_123"}}
-)
-```
-
-For more details, see [how to update state from tools](../how-tos/update-state-from-tools.ipynb).
+Tools can update agent's context (state and long-term memory) during execution. This is useful for persisting intermediate results or making information accessible to subsequent tools or prompts. See [Memory](./memory.md#read-short-term) guide for more information.