The article has no date on it, but says deferred tool loading is a recent update that occurred after the article was written. Deferred tool loading was added in Nov 2025: https://www.anthropic.com/engineering/advanced-tool-use
So these numbers are at least 7 months out of date. Why is this being posted now?
Older than that, as it implies GPT-4o is current.
The article is from May 29 2026, they're lying about that update being 'recent' and coming after the article to make themselves look better.
Deferred tool loading is not part of MCP. It's a Claude API special parameter that most other LLM APIs do not support.
+1
Its crazy that people are still discussing this. It's ancient history. Deferred tool loading, large contexts, and prompt caching have made 2026 completely different from 2025.
Also, the "CLI saves token" debate really falls apart when step one of using the CLI is running "--help". The problem remains: if knowing how to call the thing isn't in parametric memory, it has to be in context.