The SDK lets other apps (hosts) run Claude Code inside them. A PreToolUse hook runs before a tool is used. When a host's own PreToolUse hook handles the input, it can now supply the title, description and display name shown on the permission card, the prompt asking you to allow an action. This is off unless it is switched on remotely.
Claude Code ignores that text when:
- any character in it could not be shown exactly as written
- the tool's input was rewritten
The request a host gets when a tool needs permission also carries more detail, including where the deciding rule came from and whether a server policy only allows asking.
Once switched on, apps built on Claude Code can describe actions in their own words, while text that would display misleadingly is not shown.
tengu_linear_owl Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.299: off
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.299. It isn't a statement about your account. What a flag value here can and cannot tell you
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.
An [Agent SDK callback hook](/docs/en/agent-sdk/hooks) on `PreToolUse` that exceeds its timeout blocks the tool call, and Claude receives an error result naming the timeout.hooks see the edit
* **A hook**: return `"allow"` for the call from a [`PreToolUse`](/docs/en/hooks#pretooluse) hook. In [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), the workflow doesn't start on the hook's approval alone, s…workflows see the edit
Anthropic's documentation has since written up PreToolUse, on Orchestrate subagents at scale with dynamic workflows.
Fixed plan mode running a write (an MCP tool's, a file's, a shell command's) that a PreToolUse hook or a mod's tool.check hook allowed
New in this build: tengu_linear_owl