addClientAction
Allows you to equip your agents with external tools that the agent can call based on the context. these tools are defined and executed safely on the client-side without any insecure eval or code execution. What are client-side actions.
Arguments
The name of tool. it has to be unique in the agent’s scope.
Describe briefly what the tool does and when the agent should call it in natural language. make the description clear so the agent understands when to call the tool.
A Zod schema that defines the parameters. It is converted to a JSON schema that is passed to the LLM, and used to validate the LLM tool calls.
Recommended resources:
The function that will be executed when the agent calls this tool. it will be passed validated type-safe inputs based on the provided zod schema and will be executed on the client-side.
Behaviour
If you add more than 5 tools to an agent Scoopika will select the top 5 most relevant tools for each run based on the inputs.
Was this page helpful?