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)
Grammar-constrained query decomposition and intent classification.
Analyzes a research query and produces an array of PlanQuestion sub-questions, each classified as
"research"(answerable via search) or"clarify"(needs user input). Uses a JSON grammar to guarantee structured output. Returns an empty array if the query is focused enough to research directly.The harness interprets the result: all-research triggers parallel dispatch, all-clarify returns to the user, mixed drops clarify questions and dispatches only research ones.