docs: add dedicated playground section (fixes #80 & #32)

README.md

@@ -23,6 +23,7 @@ TOON achieves CSV-like compactness while adding explicit structure that helps LL
 - [Key Features](#key-features)
 - [When Not to Use TOON](#when-not-to-use-toon)
 - [Benchmarks](#benchmarks)
+- [Playgrounds](#playgrounds)
 - [📋 Full Specification](https://github.com/toon-format/spec/blob/main/SPEC.md)
 - [Installation & Quick Start](#installation--quick-start)
 - [CLI](#cli)
@@ -90,9 +91,6 @@ See [benchmarks](#benchmarks) for concrete comparisons across different data str
 
 ## Benchmarks
 
-> [!TIP]
-> Try the interactive [Format Tokenization Playground](https://www.curiouslychase.com/playground/format-tokenization-exploration) to compare token usage across CSV, JSON, YAML, and TOON with your own data.
-
 Benchmarks are organized into two tracks to ensure fair comparisons:
 
 - **Mixed-Structure Track**: Datasets with nested or semi-uniform structures (TOON vs JSON, YAML, XML). CSV excluded as it cannot properly represent these structures.
@@ -663,6 +661,13 @@ repositories[3]{id,name,repo,description,createdAt,updatedAt,pushedAt,stars,watc
 
 <!-- /automd -->
 
+## Playgrounds
+
+Experiment with TOON format interactively before installing:
+
+- **[Format Tokenization Playground](https://www.curiouslychase.com/playground/format-tokenization-exploration)** – Compare token usage across CSV, JSON (pretty/compressed), YAML, and TOON formats. Use preset datasets or paste your own data to see real-time token comparisons.
+- **[TOON Tools](https://toontools.vercel.app/)** – Full toolkit including bidirectional converters (JSON, CSV, XML, YAML ↔ TOON), token counter with side-by-side comparison, TOON validator, batch file converter, and format playground.
+
 ## Installation & Quick Start
 
 ```bash