Read-only tools set destructiveHint: false
A tool with readOnlyHint: true should set destructiveHint: false: the specification ignores destructiveHint on read-only tools, but the pair contradicts itself and OpenAI asks for false.
Check openai-readonly-destructive · OpenAI plugin directory · default severity: attention · rubric 2.1.0
What fails
The tool sets both readOnlyHint: true and destructiveHint: true, which contradict each other. The specification ignores destructiveHint on read-only tools, but OpenAI asks for false.
The rule
destructiveHint: Use false for read-only tools.
How to fix it
Set "destructiveHint": false, or set readOnlyHint to false if the tool does change data.
- On read-only tools set destructiveHint: false.
- If the tool does change data, set readOnlyHint: false instead and keep destructiveHint: true.
TypeScript SDK
import { McpServer } from '@modelcontextprotocol/server';
import * as z from 'zod';
const server = new McpServer({ name: 'issues', version: '1.0.0' });
server.registerTool(
'get_issue',
{
title: 'Get issue',
description: 'Return one issue by ID. Use when the user names an issue.',
inputSchema: z.strictObject({
issue_id: z.string().describe('Issue ID, for example ISS-42'),
}),
annotations: { readOnlyHint: true, destructiveHint: false, openWorldHint: false },
},
async ({ issue_id }) => ({ content: [{ type: 'text', text: 'Done' }] }),
);Python SDK
from typing import Annotated
from pydantic import Field
from mcp.server.mcpserver import MCPServer
from mcp.types import ToolAnnotations
server = MCPServer("issues")
@server.tool(
title="Get issue",
annotations=ToolAnnotations(readOnlyHint=True, destructiveHint=False, openWorldHint=False),
)
def get_issue(
issue_id: Annotated[str, Field(description="Issue ID, for example ISS-42")],
) -> str:
"""Return one issue by ID. Use when the user names an issue."""
return "Done"Run against @modelcontextprotocol/server 2.4.0, mcp 2.3.0 and fastmcp 4.2.2 on 2026-11-18; the checker confirms this check passes on the tool list each snippet produces.
Questions
Which value wins in clients?
Per the specification, readOnlyHint: true makes destructiveHint meaningless. Reviewers still read the pair as an error in the annotations.
Why would a server send both true?
Usually a default of destructiveHint: true applied to every tool, with readOnlyHint set per tool.
Related checks
- readOnlyHint, destructiveHint and openWorldHint are explicit booleans
- Every tool carries the applicable hint
- Tools named as writes are not marked read-only
- All checks in MCP tool annotations
How this check is graded
It counts toward: OpenAI plugin directory. See the rubric.
Last verified against OpenAI plugin guidelines, section 6.3 on 2026-11-18. The rule above is quoted in the source’s own words. This page as Markdown.
Check your tool list: paste your tools/list, nothing is sent anywhere