{"version":"2.1.315","anchor":"tool-loaded-text-capability-added-to-many-model-entries","canonical_anchor":"tool-loaded-text-capability-added-to-many-model-entries","heading":"Many models gain a new \"tool loaded text\" capability","tier":"internal","area":"Models","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.315\/e\/tool-loaded-text-capability-added-to-many-model-entries","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.315","markdown":"### Many models gain a new \"tool loaded text\" capability\n\nMany entries in Claude Code's list of model capabilities now include a capability named `tool_loaded_text`\n\n**Unclear.** It is not stated what this capability changes in how Claude Code works with these models.\n\n**What**\n\nClaude Code keeps a table of the models it supports and what each one can do. Many of those models, including Opus 4.1 era models, now list a capability called `tool_loaded_text`, which Claude Code looks up by name.\n\n**Why**\n\nModels that list this capability get whatever behaviour Claude Code ties to it, which appears to concern text shown when a tool is loaded.\n\n- Area: Models\n- Tier: Under the hood\n- Useful: 4\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no"}