top of page

Articles
About
Contact
Events
Notifications

Our Blog

All Posts
AI Ethics
Data Optimization
Generative AI
Neural Networks
AI Efficiency
Data Science
Tech Innovations
Tech Comparisons
Machine Learning
Deep Learning
Clinical Applications
LLM Model
Open Source Models
LLM
Model Fine Tuning
MCP
AI Agents
OpenAI
GPT5
Agriculture
Sustainability
Image edit
tools
RAG
RAG Pipelines
Eval
Model Evaluations

Search

Beyond Tool Calling: Why AI Agents Should Write Code to Speak with MCP

Beyond Tool Calling: Why AI Agents Should Write Code to Speak with MCP

Beyond Tool Calling: Why AI Agents Should Write Code to Speak with MCP

raditional JSON tool calling is fragile. "Code Mode" changes the game: convert MCP tools to TypeScript APIs and let AI agents write executable code. It’s faster, handles complex logic, and uses secure sandboxes. Get the full code demo here.

Dec 4, 20255 min read

Visual comparison of JSON and TOON data formats shows JSON's bloated, repetitive syntax with high token count contrasted with TOON's efficient, compact schema resulting in reduced tokens.

Visual comparison of JSON and TOON data formats shows JSON's bloated, repetitive syntax with high token count contrasted with TOON's efficient, compact schema resulting in reduced tokens.

The Efficiency Gap: Why JSON Might Be Bloating Your LLM Costs

Is JSON bloating your LLM costs? Discover TOON (Token-Oriented Object Notation), the high-efficiency alternative designed specifically for Generative AI. By decoupling schema from data, TOON can slash token usage by nearly 50% compared to standard JSON. Perfect for RAG pipelines, lowering API latency, and maximizing context windows. Check out our head-to-head code benchmark to see exactly how much syntax overhead you can eliminate today.

Nov 26, 20253 min read

Accessibility Statement

© 2026 Evnek Quest

500 Terry Francine St. San Francisco, CA 94158

bottom of page