Struct ClarificationTool 

pub struct ClarificationTool;

Ask the user a clarifying question. Pauses the agent loop until the user responds.

When used with run_loop_interactive, the loop calls on_input(question) and injects the user’s response as the tool result. With plain run_loop, emits LoopEvent::WaitingForInput and continues with a placeholder.

Trait Implementations

impl Tool for ClarificationTool

fn name(&self) -> &str

Unique tool name (used as discriminator in LLM function calling).

fn description(&self) -> &str

Human-readable description shown to the LLM.

fn is_system(&self) -> bool

System tools are always visible (not subject to progressive discovery).

fn parameters_schema(&self) -> Value

JSON Schema for the tool’s parameters (generated via json_schema_for::<Args>()).

fn execute<'life0, 'life1, 'async_trait>( &'life0 self, args: Value, _ctx: &'life1 mut AgentContext, ) -> Pin<Box<dyn Future<Output = Result<ToolOutput, ToolError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

fn is_read_only(&self) -> bool

Read-only tools can execute in parallel via execute_readonly.

fn execute_readonly<'life0, 'life1, 'async_trait>( &'life0 self, args: Value, ctx: &'life1 AgentContext, ) -> Pin<Box<dyn Future<Output = Result<ToolOutput, ToolError>> + Send + 'async_trait>>

where 'life0: 'async_trait, 'life1: 'async_trait, Self: 'async_trait,

Execute without mutable context (for parallel read-only dispatch). Default: delegates to execute with a cloned context. Override for true read-only tools to avoid the clone.

fn to_def(&self) -> ToolDef