From 8bcbdb7315917fbf6e25db6b8380402a24811e0b Mon Sep 17 00:00:00 2001
From: Johann Schopplich <mail@johannschopplich.com>
Date: Sat, 1 Nov 2025 07:53:48 +0100
Subject: [PATCH] docs: enhance explanation for TOON format benefits (related
 to #49)

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index a5dfd63..8f68a17 100644
--- a/README.md
+++ b/README.md
@@ -52,9 +52,9 @@ users[2]{id,name,role}:
 ```
 
 <details>
-<summary>Another reason</summary>
+<summary><strong>Why create a new format?</strong></summary>
 
-[![xkcd: Standards](https://imgs.xkcd.com/comics/standards_2x.png)](https://xkcd.com/927/)
+For small payloads, JSON/CSV/YAML work fine. TOON's value emerges at scale: when you're making hundreds of LLM calls with uniform tabular data, eliminating repeated keys compounds savings significantly. If token costs matter to your use case, TOON reduces them. If not, stick with what works.
 
 </details>