# The tools/list result carries resultType

**Revision 2026-07-28 requires every result to carry resultType, which is "complete" for tools/list; clients treat a missing value as "complete" from an older server, but a 2026-07-28 server must send it.**

Check `spec-envelope-result-type` · MCP specification 2026-07-28 · default severity: attention (or blocking, advice, depending on the case) · rubric 2.1.0. Last verified against MCP schema.ts, revision 2026-07-28 on 2026-11-18.

## What fails

Revision 2026-07-28 adds a required resultType to every result ("complete" for tools/list). Clients treat a missing value as "complete" from older servers. It is attention when the answer otherwise looks like 2026-07-28, advice when it looks older, and blocking when the value is not "complete".

## The rule

> Servers implementing this protocol version MUST include this field.

Source: [MCP schema.ts, revision 2026-07-28](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2026-07-28/schema.ts)

## How to fix it

Add "resultType": "complete" to the tools/list result.

1. Upgrade to an SDK that implements 2026-07-28 (TypeScript @modelcontextprotocol/server 2.x, Python mcp 2.x): they add resultType for you.
2. In a hand-written server or proxy, add "resultType": "complete" to the tools/list result.
3. Never send another value for tools/list.

### TypeScript SDK

```ts
import { McpServer } from '@modelcontextprotocol/server';
import * as z from 'zod';

const server = new McpServer({ name: 'issues', version: '1.0.0' }, { cacheHints: { 'tools/list': { ttlMs: 300000, cacheScope: 'private' } } });

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

```python
from typing import Annotated

from pydantic import Field
from mcp.server.mcpserver import MCPServer
from mcp.types import ToolAnnotations
from mcp.server.caching import CacheHint

server = MCPServer("issues", cache_hints={"tools/list": CacheHint(ttl_ms=300_000, scope="private")})

@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"
```

## Questions

### What other values can resultType have?

"complete" for a finished result and "input_required" when the server needs more input from the client first. tools/list is always complete.

### Will older clients break on the new field?

No. Unknown result fields are ignored by older clients.

## Related checks

- [The tools/list result carries ttlMs and cacheScope](https://isokron.ai/mcp-check/checks/spec-envelope-cache)
- [The paste holds the whole tool list](https://isokron.ai/mcp-check/checks/spec-pagination-partial)
- [No tool-level execution field from 2025-11-25](https://isokron.ai/mcp-check/checks/spec-execution-legacy)
- [MCP specification 2026-07-28: tools/list rules](https://isokron.ai/mcp-check/checks/protocol)

## Further reading

- [Shipping a production MCP server on the 2026-07-28 spec](https://isokron.ai/research/production-mcp-server)

Counts toward: MCP specification 2026-07-28.

Rubric: https://isokron.ai/mcp-check/rubric

Check your tool list: https://isokron.ai/mcp-check
