{"version":"2.1.304","anchor":"denied-tool-reminder-lead-and-unverified-memory-content","canonical_anchor":"denied-tool-reminder-lead-and-unverified-memory-content","heading":"Tool reminders can list denied tools first, and unverified memory is shown differently","tier":"internal","area":"Elsewhere","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.304\/e\/denied-tool-reminder-lead-and-unverified-memory-content","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.304","markdown":"### Tool reminders can list denied tools first, and unverified memory is shown differently\n\nThe reminder Claude gets about unavailable tools can now put denied tools first under their own line, and unverified memory is presented differently\n\n**What**\n\nClaude Code adds short notes called system reminders to the conversation so the model knows about its situation. One of them tells the model which tools are held back or no longer available, and why.\n\n- Denied tools can now be listed first, under a separate opening line, instead of being mixed in with the other reasons a tool was removed.\n\n- A memory item attached to the conversation that is marked as unverified is now presented to the model in a different way from verified memory.\n\n**Why**\n\nThese change the reminders the model sees, which can affect how it talks about tools it cannot use and how it treats memory that has not been checked.\n\n- Area: Elsewhere\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}