Update How-to Guides (#417)

- reduce the number of API keys needed (Use simple tool)
- make everything "tool use" oriented rather than split across agent executor, function calling, tool use, etc.
- Reorg navbar and index
- Fixup some docstrings
- Add more links to ref docs
- Mix up models used
- Simplify a few examples

docs/docs/reference/checkpoints.md

@@ -1,6 +1,6 @@
 # Checkpoints
 
-You can [compile](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.MessageGraph.compile) any LangGraph workflow with a [CheckPointer](https://langchain-ai.github.io/langgraph/reference/checkpoints/#checkpoint) to give your agent "memory" by persisting its state. This permits things like:
+You can [compile](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.MessageGraph.compile) any LangGraph workflow with a [CheckPointer](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver) to give your agent "memory" by persisting its state. This permits things like:
 
 - Remembering things across multiple interactions
 - Interrupting to wait for user input

docs/docs/reference/errors.md

@@ -0,0 +1,6 @@
+# Errors
+
+While you may not want to see them, informative errors help you design better workflows.
+Below are the LangGraph-specific errors and what they mean.
+
+::: langgraph.errors