What
An MCP (Model Context Protocol, the standard Claude Code uses to connect external tools) tool's manifest can now set several behaviors through _meta fields:
anthropic/maxResultSizeCharsoverrides the tool's default maximum result size, up to an internal ceilinganthropic/requiresUserInteractionforces a permission prompt before the tool runsanthropic/alwaysLoadforces the tool to always be loadedanthropic/searchHint(orpromptOverrides.search_hints) supplies a searchable hint string for the tool
Why
This gives MCP tool authors finer control over how their tools behave in Claude Code, such as allowing larger results when needed, requiring explicit confirmation, or improving discoverability, without relying only on Claude Code's built-in defaults.
Names in the bundle_meta
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Hooks reference touched a line naming _meta after this was published.
An MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval prompt with `"allow"`, with or without `updatedInput`, bec…hooks see the edit
Confirmed since
Anthropic's documentation has since written up _meta, on SEP-2640: Skills Extension.
* [Skill `_meta` Keys](https://github.com/modelcontextprotocol/ext-skills/blob/main/docs/archive/skill-meta-keys.md): `_meta` key conventions for skill resourcesseps/2640-skills-extension see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up _meta, on SEP-2640: Skills Extension.