{"version":"2.1.281","anchor":"tool-result-size-telemetry-token-estimate-media-count-wil","canonical_anchor":"tool-result-size-telemetry-token-estimate-media-count-wil","heading":"Tool-result size telemetry: token estimate, media count, will-persist flag","tier":null,"area":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281\/e\/tool-result-size-telemetry-token-estimate-media-count-wil","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.281","markdown":"### Tool-result size telemetry: token estimate, media count, will-persist flag\n\nUsage data now records a tool result's estimated tokens, image and document count, and whether it will be saved to disk\n\n**What**\n\nA tool result is what a tool hands back to Claude after it runs. A new helper records three measurements of it in usage data:\n\n- `toolResultTokensEst`, an estimate of its size in tokens (the units the model reads text in)\n\n- `toolResultMediaBlocks`, how many images or documents it contains\n\n- `toolResultWillPersist`, whether it is large enough to be saved rather than kept inline\n\nIf the measurement fails, the error is ignored.\n\n**Why**\n\nThis adds measurement only. A failure inside it never interrupts the tool call."}