ReadonlydescriptionHuman-readable description shown to the model
ReadonlynameTool name — used as the function identifier in tool calls
ReadonlyparametersJSON Schema describing the tool's expected arguments
Execute the tool with parsed arguments
Called by the agent pool when the model emits a tool call matching this tool's name. The return value is JSON-serialized and prefilled back into the agent's context as a tool result.
Returns an Effection Operation — implement as a generator method. The operation runs inside the agent pool's scope, so it has access to Ctx, Store, and Events contexts for nested agent spawning.
Parsed arguments from the model's tool call
Tool result (will be JSON-serialized)
Inject the toolkit that sub-agents will use. Must be called before execute.
Spawn parallel web-research sub-agents for a set of questions.
Similar to ResearchTool but designed for web-source pipelines. Each question gets its own agent in a shared-root pool with access to web_search, fetch_page, and report tools. Hard-cut agents that exhaust their turns without reporting get a grammar-constrained scratchpad extraction via generate to recover partial findings.
Must call setToolkit before the tool is executed.