Clarify host behavior for rendering an MCP App view when the tool result is an error (isError: true)

Summary

The spec defines how a host renders a view once a tool with a ui.resourceUri returns, but it doesn't say what a host should do when that tool call returns an error result (isError: true). Hosts are diverging, and I'd like a recommendation (ideally normative) so implementations stay consistent.

• ChatGPT unmount the view iframe (it was already mounted when the output was received)
• Claude doesn't mount the view iframe
• Goose keep the iframe mounted and proceed with rendering as usual. The isError value is not accessible from the view.

What the spec covers today

The ui/notifications/tool-result notification and the rendering flow describe the success path (result.content / structuredContent are forwarded to the view). There's ui/notifications/tool-cancelled for cancellation, but nothing addresses a completed tool call whose result has isError: true, e.g.:

{
  "content": [{ "type": "text", "text": "My custom error message returned from tool" }],
  "isError": true,
}

Questions

• When a tool result has isError: true, should the host skip rendering the view and fall back to the normal error/text presentation?
• If the view is still rendered, should the host deliver the error via ui/notifications/tool-result (with isError preserved), via a distinct signal, or not at all? If the same notification is used, how to access the isError boolean?

Read specification/2026-01-26/apps.mdx, especially ui/notifications/tool-result and the rendering flow, and compare the host behaviors described here. Done means the specification gives a decided, normative rule for isError: true results, including whether views render and how any error state reaches them.