Skip to content

Match tool results' structure to that of prompts #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jspahrsummers merged 1 commit into from
Nov 6, 2024
Merged

Match tool results' structure to that of prompts #37

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions docs/spec/tools.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,19 +236,20 @@ Example:

The server MUST respond with a `CallToolResult` containing:

- `toolResult`: The result of the tool invocation (any JSON-serializable value)
- `content`: An array of content items that can be text, images, or embedded resources
- `isError`: A boolean indicating whether this result represents an error state

Example:
```json
{
"jsonrpc": "2.0",
"id": 2,
"result": {
"toolResult": {
"temperature": 72,
"humidity": 65,
"description": "Partly cloudy"
}
"content": [{
"type": "text",
"text": "Current weather in New York:\nTemperature: 72°F\nHumidity: 65%\nConditions: Partly cloudy"
}],
"isError": false
}
}
```
Expand Down
75 changes: 47 additions & 28 deletions schema/schema.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,17 +54,36 @@
"type": "object"
},
"CallToolResult": {
"description": "The server's response to a tool call.\n\nAny errors that originate from the tool SHOULD be reported inside the result\nobject—i.e., as part of an MCP successful result, not as an MCP error\nresponse. Otherwise, the LLM would not be able to see that an error occurred\nand self-correct.\n\nHowever, any errors in _finding_ the tool, an error indicating that the\nserver does not support tool calls, or any other exceptional conditions,\nshould be reported as an MCP error response.",
"description": "The server's response to a tool call.\n\nAny errors that originate from the tool SHOULD be reported inside the result\nobject, with `isError` set to true, _not_ as an MCP protocol-level error\nresponse. Otherwise, the LLM would not be able to see that an error occurred\nand self-correct.\n\nHowever, any errors in _finding_ the tool, an error indicating that the\nserver does not support tool calls, or any other exceptional conditions,\nshould be reported as an MCP error response.",
"properties": {
"_meta": {
"additionalProperties": {},
"description": "This result property is reserved by the protocol to allow clients and servers to attach additional metadata to their responses.",
"type": "object"
},
"toolResult": {}
"content": {
"items": {
"anyOf": [
{
"$ref": "#/definitions/TextContent"
},
{
"$ref": "#/definitions/ImageContent"
},
{
"$ref": "#/definitions/EmbeddedResource"
}
]
},
"type": "array"
},
"isError": {
"type": "boolean"
}
},
"required": [
"toolResult"
"content",
"isError"
],
"type": "object"
},
Expand Down Expand Up @@ -366,6 +385,30 @@
"description": "An opaque token used to represent a cursor for pagination.",
"type": "string"
},
"EmbeddedResource": {
"description": "The contents of a resource, embedded into a prompt or tool call result.\n\nIt is up to the client how best to render embedded resources for the benefit\nof the LLM and/or the user.",
"properties": {
"resource": {
"anyOf": [
{
"$ref": "#/definitions/TextResourceContents"
},
{
"$ref": "#/definitions/BlobResourceContents"
}
]
},
"type": {
"const": "resource",
"type": "string"
}
},
"required": [
"resource",
"type"
],
"type": "object"
},
"EmptyResult": {
"$ref": "#/definitions/Result"
},
Expand Down Expand Up @@ -1171,30 +1214,6 @@
],
"type": "object"
},
"PromptEmbeddedResource": {
"description": "The contents of a resource, embedded into a prompt.\n\nIt is up to the client how best to render embedded resources for the benefit\nof the LLM and/or the user.",
"properties": {
"resource": {
"anyOf": [
{
"$ref": "#/definitions/TextResourceContents"
},
{
"$ref": "#/definitions/BlobResourceContents"
}
]
},
"type": {
"const": "resource",
"type": "string"
}
},
"required": [
"resource",
"type"
],
"type": "object"
},
"PromptListChangedNotification": {
"description": "An optional notification from the server to the client, informing it that the list of prompts it offers has changed. This may be issued by servers without any previous subscription from the client.",
"properties": {
Expand Down Expand Up @@ -1231,7 +1250,7 @@
"$ref": "#/definitions/ImageContent"
},
{
"$ref": "#/definitions/PromptEmbeddedResource"
"$ref": "#/definitions/EmbeddedResource"
}
]
},
Expand Down
13 changes: 7 additions & 6 deletions schema/schema.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ export type JSONRPCMessage =
| JSONRPCResponse
| JSONRPCError;

export const LATEST_PROTOCOL_VERSION = "2024-10-07";
export const LATEST_PROTOCOL_VERSION = "2024-11-05";
export const JSONRPC_VERSION = "2.0";

/**
Expand Down Expand Up @@ -562,16 +562,16 @@ export interface PromptArgument {
*/
export interface PromptMessage {
role: "user" | "assistant";
content: TextContent | ImageContent | PromptEmbeddedResource;
content: TextContent | ImageContent | EmbeddedResource;
}

/**
* The contents of a resource, embedded into a prompt.
* The contents of a resource, embedded into a prompt or tool call result.
*
* It is up to the client how best to render embedded resources for the benefit
* of the LLM and/or the user.
*/
export interface PromptEmbeddedResource {
export interface EmbeddedResource {
type: "resource";
resource: TextResourceContents | BlobResourceContents;
}
Expand Down Expand Up @@ -602,7 +602,7 @@ export interface ListToolsResult extends PaginatedResult {
* The server's response to a tool call.
*
* Any errors that originate from the tool SHOULD be reported inside the result
* object—i.e., as part of an MCP successful result, not as an MCP error
* object, with `isError` set to true, _not_ as an MCP protocol-level error
* response. Otherwise, the LLM would not be able to see that an error occurred
* and self-correct.
*
Expand All @@ -611,7 +611,8 @@ export interface ListToolsResult extends PaginatedResult {
* should be reported as an MCP error response.
*/
export interface CallToolResult extends Result {
toolResult: unknown;
content: (TextContent | ImageContent | EmbeddedResource)[];
isError: boolean;
}

/**
Expand Down