docs: feedback edits (#5387)

docs/docs/how-tos/graph-api.md

@@ -658,7 +658,7 @@ print(graph.invoke({}, {"configurable": {"my_runtime_value": "b"}}))
 
 There are many use cases where you may wish for your node to have a custom retry policy, for example if you are calling an API, querying a database, or calling an LLM, etc. LangGraph lets you add retry policies to nodes.
 
-To configure a retry policy, pass the `retry_policy` parameter to the [add_node](https://langchain-ai.github.io/langgraph/reference/graphs.md#langgraph.graph.state.StateGraph.add_node). The `retry_policy` parameter takes in a `RetryPolicy` named tuple object. Below we instantiate a `RetryPolicy` object with the default parameters and associate it with a node:
+To configure a retry policy, pass the `retry_policy` parameter to the [add_node](../reference/graphs.md#langgraph.graph.state.StateGraph.add_node). The `retry_policy` parameter takes in a `RetryPolicy` named tuple object. Below we instantiate a `RetryPolicy` object with the default parameters and associate it with a node:
 
 ```python
 from langgraph.pregel import RetryPolicy

docs/docs/how-tos/tool-calling.md

@@ -344,6 +344,8 @@ tool_node.invoke({"messages": [...]})
 
 ## Tool customization
 
+For more control over tool behavior, use the `@tool` decorator.
+
 ### Parameter descriptions
 
 Auto-generate descriptions from docstrings: