Unverified50% confidenceBenchmarkExact time
In the official example response, 61 state_tokens are used for the invoice text and 472 schema_tokens for the field definitions, totaling 655 input_tokens, with output_tokens of 0 and passes of 3.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedThe schema of the single Read tool in claude-code consumes 7,487 tokens.67% similarUnverifiedIn the benchmark's git log sample, the script uses split(" ")[4] assuming the fifth word on each line is the commit type, but this only holds when the author's name is two words; the tester ran the same script on context-mode's own commit history (2,234 commits, 203 KB), and the summary output went from 107 bytes to 7,071 bytes, a 96.5% savings, but the output wrongly showed the most common type as 'update', when in fact 550 commits came from the single-word author name github-actions[bot].65% similarUnverifiedThe developer defined "recovery-type" sessions as 10 in total with 1,636 messages combined, and "publishing-type" sessions as 3 in total with 536 messages combined; the 1,327-message session was thrown into "uncategorized" because it could not be assigned to either of these two categories.64% similarUnverifiedThe read_tool_output session reader accepts a result ID, a UTF-8 byte offset, and a paging cap of at most 4096 bytes, and returns the five fields text, nextOffset, totalBytes, hasMore, and complete.63% similarUnverifiedIn tool-call statistics of about 1,900 messages, the 10 `browser_*` tools, `text_to_speech`, `clarify`, and `process` had zero calls.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1075174API
curl https://kongchang.com/api/v1/knowledge/claims/1075174MCP
get_claim(id=1075174)