Manual and Mandatory Tool Call

These two blocks allow you to perform highly controlled calling of tools and storing of results.

• The Mandatory Tool Call block uses an LLM to build the arguments to pass to a tool, then forces exactly one call to that tool.

• The Manual Tool Call block does not use an LLM to build the tool call. Instead, you define the tool arguments directly in the block by using CEL expressions.

Output

You can then decide what to do with the output of the tool call:

• Store it into the state

• Store it into the scratchpad

• Add it to the conversation history, so that it can be picked up by subsequent Agentic Loop or LLM Request blocks