{"version":"2.1.307","anchor":"the-agent-tool-description-in-the-command-team-onboarding-pr","canonical_anchor":"the-agent-tool-description-in-the-command-team-onboarding-pr","heading":"Agent tool guidance rewritten in the team onboarding prompt","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307\/e\/the-agent-tool-description-in-the-command-team-onboarding-pr","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307","markdown":"### Agent tool guidance rewritten in the team onboarding prompt\n\nThe instructions on when Claude hands work to a helper agent were reworded in the team onboarding prompt, noting you can only wait or cancel\n\n**What**\n\nThe description of the `Agent` tool was rewritten in the prompt Claude Code sends for the team onboarding command. The `Agent` tool is how Claude passes a piece of work to a subagent, a separate helper copy of Claude that works on it and reports back.\n\nThe old text opened with a list of situations where delegating made sense. The new text includes a reminder about what the person using Claude Code sees while a helper runs:\n\n- \"You can't watch it work, only wait or cancel.\"\n\n**Why**\n\nThis text is part of Claude's own instructions, so the rewrite changes how Claude weighs handing work off. The new line tells Claude that delegated work is out of your view until it finishes, which can make it less eager to delegate.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}