Struct ManagedCustomTool 

pub struct ManagedCustomTool { /* private fields */ }

Wrapper for custom (client-executed) tools declared in a ManagedAgentDef.

When the Runner’s agent calls execute(), this tool returns a pending status and signals is_long_running() = true. This causes the agent loop to break after the current turn, yielding control back to the session loop. The session loop then emits agent.custom_tool_use to notify the client and parks via the ToolParkingLot until the client delivers a result through user.custom_tool_result.

Multi-Turn Flow

1. LLM returns a function call for this custom tool
2. Agent calls execute() → returns pending status
3. is_long_running() = true breaks the agent loop
4. Session loop sees the custom tool call in emitted events
5. Session loop emits agent.custom_tool_use, sets RequiresAction stop reason
6. Session loop parks until client delivers via user.custom_tool_result
7. On next turn, the delivered result is available for the agent

Implementations

impl ManagedCustomTool

pub fn new(name: String, description: String, input_schema: Value) -> Self

Create a new custom tool wrapper.

Arguments

• name — Tool name as declared in the agent definition.
• description — Human-readable description for the LLM.
• input_schema — JSON Schema for the tool’s input parameters.

Trait Implementations

impl Clone for ManagedCustomTool

fn clone(&self) -> ManagedCustomTool

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ManagedCustomTool

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Tool for ManagedCustomTool

fn name(&self) -> &str

Returns the unique name of this tool.

fn description(&self) -> &str

Returns a human-readable description of what this tool does.

fn parameters_schema(&self) -> Option<Value>

Returns the JSON Schema for this tool’s parameters, if any.

fn is_long_running(&self) -> bool

Indicates whether the tool is a long-running operation. Long-running tools typically return a task ID immediately and complete the operation asynchronously.

fn execute<'life0, 'async_trait>( &'life0 self, _ctx: Arc<dyn ToolContext>, args: Value, ) -> Pin<Box<dyn Future<Output = Result<Value>> + Send + 'async_trait>>

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

Executes the tool with the given context and arguments.

fn declaration(&self) -> Value

Returns the tool declaration that should be exposed to model providers.

fn enhanced_description(&self) -> String

Returns an enhanced description that may include additional notes. For long-running tools, this includes a warning not to call the tool again if it has already returned a pending status. Default implementation returns the base description.

fn is_builtin(&self) -> bool

Indicates whether this tool is a built-in server-side tool (e.g., google_search, url_context).

fn response_schema(&self) -> Option<Value>

Returns the JSON Schema for this tool’s response, if any.

fn required_scopes(&self) -> &[&str]

Returns the scopes required to execute this tool.

fn is_read_only(&self) -> bool

Indicates whether this tool performs no side effects. Read-only tools may be executed concurrently in Auto mode.

fn is_concurrency_safe(&self) -> bool

Indicates whether this tool is safe for concurrent execution. Used by the Parallel strategy to validate dispatch safety.