add ToolRuntime migration section to tools documentation (#1737)

Author: BenHavis

src/oss/langchain/tools.mdx

@@ -167,6 +167,8 @@ The following parameter names are reserved and cannot be used as tool arguments.
 | `runtime` | Reserved for `ToolRuntime` parameter (accessing state, context, store) |
 
 To access runtime information, use the @[`ToolRuntime`] parameter instead of naming your own arguments `config` or `runtime`.
+
+If you use `InjectedState`, `InjectedStore`, `get_runtime()`, or `InjectedToolCallId`, see [Migrate from older injection patterns](#migrate-from-older-injection-patterns).
 :::
 
 ## Access context
@@ -621,6 +623,40 @@ Requires `deepagents>=1.9.0` (or `@langchain/langgraph>=1.2.8`).
 </Note>
 :::
 
+:::python
+<Accordion title="Migrate from older injection patterns" id="migrate-from-older-injection-patterns">
+
+Older examples used `InjectedState`, `InjectedStore`, `get_runtime()`, or `InjectedToolCallId`. Use @[`ToolRuntime`] instead for one explicit interface to state, context, store, and execution metadata.
+
+#### Previous pattern
+
+```python
+from langchain.tools import tool, InjectedState
+
+@tool
+def summarize(state: InjectedState) -> str:
+    """Summarize the conversation."""
+    messages = state["messages"]
+    return f"Conversation length: {len(messages)} messages."
+```
+
+#### Recommended pattern
+
+```python
+from langchain.tools import tool, ToolRuntime
+
+@tool
+def summarize(runtime: ToolRuntime) -> str:
+    """Summarize the conversation."""
+    messages = runtime.state["messages"]
+    return f"Conversation length: {len(messages)} messages."
+```
+
+For agent-level migrations (for example `create_react_agent` and custom state), see the [LangChain v1 migration guide](/oss/migrate/langchain-v1).
+
+</Accordion>
+:::
+
 ## Tool execution
 
 In LangChain, tools are used by agents (for example via @[`create_agent`]) and tool error handling is configured through [middleware](/oss/langchain/middleware).
@@ -727,10 +763,9 @@ Handle tool errors using LangChain agent [middleware](/oss/langchain/middleware)
 
 ### State injection
 
-Tools can access the current graph state through @[`ToolRuntime`]:
+Tools access graph state through @[`ToolRuntime`]. See [Access context](#access-context) for state, context, store, and streaming APIs.
 
 :::python
-
 ```python
 from langchain.tools import tool, ToolRuntime
 
@@ -740,12 +775,8 @@ def get_message_count(runtime: ToolRuntime) -> str:
     messages = runtime.state["messages"]
     return f"There are {len(messages)} messages."
 ```
-
 :::
 
-For more details on accessing state, context, and long-term memory from tools, see [Access context](#access-context).
-
-
 ## Dynamic tool selection
 
 With dynamic tools, the set of tools available to the agent is modified at runtime rather than defined all upfront. Not every tool is appropriate for every situation. Too many tools may overwhelm the model (overload context) and increase errors; too few limit capabilities. Dynamic tool selection enables adapting the available toolset based on authentication state, user permissions, feature flags, or conversation stage.