Struct ToolResult 

pub struct ToolResult {
    pub tool_call_id: String,
    pub content: String,
    pub success: bool,
}

The outcome of executing a ToolCall.

Important: failures are context, not errors

A ToolResult with success: false is not a Rust-level error — it is domain data that gets appended to the conversation as an AgentMessage::Tool entry so the model can observe the failure and adjust its strategy (retry, fix arguments, use a different tool, etc.).

Infrastructure-level failures (e.g. the MCP process crashed) are surfaced separately via anyhow::Error from crate::ports::ToolExecutorPort::execute and then converted by the loop implementation into a ToolResult with success: false and an appropriate content describing the outage.

Fields

tool_call_id: String

Echoes the ToolCall::id this result corresponds to.

content: String

Human-readable output (or error message) from the tool execution.

success: bool

Whether the tool completed successfully.

false here is not a loop error — see type-level docs above.

Trait Implementations

impl Clone for ToolResult

fn clone(&self) -> ToolResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ToolResult

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ToolResult

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ToolResult

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.