{"version":"2.1.286","anchor":"prompt-snapshot-tool-replay-schema-comparison-reworked","canonical_anchor":"prompt-snapshot-tool-replay-schema-comparison-reworked","heading":"Finer internal reporting when recorded tool definitions are compared","tier":"internal","area":"Tools","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/prompt-snapshot-tool-replay-schema-comparison-reworked","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Finer internal reporting when recorded tool definitions are compared\n\nComparing recorded tool definitions now gives a more detailed result than yes or no, and an error during the check is caught\n\n**What**\n\nClaude Code can compare a previously recorded set of tool definitions against the current ones. A tool definition is the description Claude Code gives the model of each action it can take. That comparison used to give only a yes-or-no answer, with two kinds of mismatch. It now sorts the result into finer categories, grouped by family of recorded item.\n\nIf the comparison itself fails with an error, Claude Code now catches that error rather than letting it escape.\n\n**Why**\n\nThis only affects Claude Code's internal usage reporting. Nothing you see or do changes.\n\n- Area: Tools\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5"}