Struct CallToolResult 

#[non_exhaustive]
pub struct CallToolResult {
    pub content: Vec<ContentBlock>,
    pub structured_content: Option<Value>,
    pub is_error: Option<bool>,
    pub meta: Option<Meta>,
}

The result of a tool call operation.

Contains the content returned by the tool execution and an optional flag indicating whether the operation resulted in an error.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

content: Vec<ContentBlock>

The content returned by the tool (text, images, etc.)

structured_content: Option<Value>

An optional JSON object that represents the structured result of the tool call

is_error: Option<bool>

Whether this result represents an error condition

meta: Option<Meta>

Optional protocol-level metadata for this result

Implementations

impl CallToolResult

pub fn success(content: Vec<ContentBlock>) -> Self

Create a successful tool result with unstructured content

pub fn error(content: Vec<ContentBlock>) -> Self

Create a tool-level error result with caller-visible content.

When to use this vs Err(ErrorData)

MCP distinguishes two failure modes for a call_tool invocation, and the right one to use depends on whose problem it is:

• Tool-level error — Ok(CallToolResult::error(...)). The request was valid and routed to your tool, but executing the tool failed in a way the caller should see (a query returned no rows, an external API returned 500, the user’s input is plausible but produced no result, etc.). The caller’s MCP client renders the content you provide; your message reaches the user. This is the right choice for almost every “the tool ran and didn’t work” case.

• Protocol error — Err(ErrorData) with a JSON-RPC code. The server cannot route the request at all, or an infrastructure error makes the server itself unusable (ErrorCode::INTERNAL_ERROR, -32603). MCP clients typically render protocol errors opaquely (e.g. “Tool result missing due to internal error”) — the caller does not see your message.

Example

use rmcp::model::{CallToolResult, Content, ErrorData};

async fn lookup(query: &str) -> Result<CallToolResult, ErrorData> {
    // Caller passed a malformed query — the server can't run anything.
    // This is a protocol error, the caller's client will render it
    // as -32602 invalid_params:
    if query.is_empty() {
        return Err(ErrorData::invalid_params("query must be non-empty", None));
    }

    // Tool ran, no result. Caller should see the explanation:
    let rows = run_query(query).await;
    if rows.is_empty() {
        return Ok(CallToolResult::error(vec![ContentBlock::text(
            format!("no rows matched '{query}'"),
        )]));
    }

    Ok(CallToolResult::success(vec![ContentBlock::text(format_rows(&rows))]))
}

pub fn structured(value: Value) -> Self

Create a successful tool result with structured content

Example

use rmcp::model::CallToolResult;
use serde_json::json;

let result = CallToolResult::structured(json!({
    "temperature": 22.5,
    "humidity": 65,
    "description": "Partly cloudy"
}));

pub fn structured_error(value: Value) -> Self

Create an error tool result with structured content

Example

use rmcp::model::CallToolResult;
use serde_json::json;

let result = CallToolResult::structured_error(json!({
    "error_code": "INVALID_INPUT",
    "message": "Temperature value out of range",
    "details": {
        "min": -50,
        "max": 50,
        "provided": 100
    }
}));

pub fn with_meta(self, meta: Option<Meta>) -> Self

Set the metadata on this result

pub fn into_typed<T>(self) -> Result<T, Error>

where T: DeserializeOwned,

Convert the structured_content part of response into a certain type.

About json schema validation

Since rust is a strong type language, we don’t need to do json schema validation here.

But if you do have to validate the response data, you can use jsonschema crate.

Trait Implementations

impl Clone for CallToolResult

fn clone(&self) -> CallToolResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CallToolResult

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

Formats the value using the given formatter.

impl Default for CallToolResult

fn default() -> CallToolResult

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for CallToolResult

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<CallToolResult> for ServerResult

fn from(value: CallToolResult) -> Self

Converts to this type from the input type.

impl IntoCallToolResult for CallToolResult

Available on crate feature server only.

fn into_call_tool_result(self) -> Result<CallToolResult, ErrorData>

impl JsonSchema for CallToolResult

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for CallToolResult

fn eq(&self, other: &CallToolResult) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for CallToolResult

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for CallToolResult