{"version":"2.1.252","anchor":"contextcost-breakdown-now-counts-tool-descriptions-from-a-r","canonical_anchor":"contextcost-breakdown-now-counts-tool-descriptions-from-a-r","heading":"Context\/cost breakdown now counts tool descriptions from a recorded prompt snapshot","tier":"internal","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.252\/e\/contextcost-breakdown-now-counts-tool-descriptions-from-a-r","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.252","markdown":"### Context\/cost breakdown now counts tool descriptions from a recorded prompt snapshot\n\nContext\/cost breakdowns like \/context now reuse the exact tool description text actually sent, for accuracy.\n\nThe token-counting helpers for MCP tools, built-in tools, skills, and slash commands (`dA`, formerly `TA`) now accept a `recordedDescription` map sourced from the last prompt snapshot, so re-analysis of context usage (e.g. `\/context`) reuses the exact tool description text actually sent to the model instead of recomputing it.\n\n- Flag `tengu_carved_slate`: Off in both readings (read for one account on one subscription tier against v2.1.252; this account: off, anonymous baseline: off, compiled default: not a boolean we can read)\n- Area: Elsewhere\n- Names: `\/context`\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}