{"version":"2.1.323","anchor":"unrun-tool-calls-get-clearer-wording-with-call-it-again-a","canonical_anchor":"unrun-tool-calls-get-clearer-wording-with-call-it-again-a","heading":"Clearer wording for tool calls that may not have run","tier":"notice","area":"Tool Calls","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/unrun-tool-calls-get-clearer-wording-with-call-it-again-a","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Clearer wording for tool calls that may not have run\n\nWhen a tool call has no result, the model is now told plainly it may not have run, with advice to retry or check first\n\n**What**\n\nA tool call is a single action the model asks Claude Code to take, such as running a command. When one ends with no result, for example after an interruption, the model now gets one of two messages:\n\n- \"As far as this session knows, this call did not run.\"\n\n- \"This call has no result. It may not have run, or not completely.\"\n\nClaude Code then adds advice either to call it again or to check first, unless that advice is switched off for the case at hand.\n\n**Why**\n\nWhat the model is told after an interrupted action shapes whether it repeats it. The second wording warns that the action may have partly happened, so the model is steered to check before running it again.\n\n- Area: Tool Calls\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}