{"version":"2.1.323","anchor":"script-tool-refusals-summary","canonical_anchor":"script-tool-refusals-summary","heading":"Claude is told which tool calls were refused while a script ran","tier":"notice","area":"REPL","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/script-tool-refusals-summary","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Claude is told which tool calls were refused while a script ran\n\nAfter a script runs, Claude Code can now give the model a list of the tool calls that were refused while it ran\n\n**What**\n\nClaude Code can now put together a list of the tool calls that were refused while a script ran. A tool call is one action Claude takes, such as reading a file or running a command. The list shows up to 10 further entries, and each one is cut off at 500 characters.\n\n**Why**\n\nThe model can see which of its scripted actions were refused and why, instead of guessing at what went wrong.\n\n- Area: REPL\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}