menix
Why? Because when you pair output schema with CodeAct agents (agents that reason and act by writing executable code rather than natural language, like smolagents by Hugging Face), you solve some of the most painful problems in agentic tool use:
1. Context window waste: Without output schema, agents have to call a tool, dump the raw output (often massive JSON blobs) into the context window, inspect it, and only then write code to handle it. That "print-and-inspect" pattern burns tokens and attention on data the agent shouldn't need to explore in the first place.
2. Roundtrip overhead: Writing large payloads back into tools has the same problem in reverse. Structured schemas on both input and output let the agent plan a precise, single-step program instead of fumbling through multiple exploratory turns.
There's a blog post on Hugging Face that demonstrates this concretely using smolagents: https://huggingface.co/blog/llchahn/ai-agents-output-schema
And the industry is clearly converging on this pattern. Cloudflare built their "Code Mode" around the same idea (https://blog.cloudflare.com/code-mode/), converting MCP tools into a TypeScript API and having the LLM write code against it rather than calling tools directly. Their core finding: LLMs are better at writing code to call MCP than at calling MCP directly. Anthropic followed with "Programmatic tool calling" (https://www.anthropic.com/engineering/code-execution-with-mc..., https://platform.claude.com/docs/en/agents-and-tools/tool-us...), where Claude writes Python code that calls tools inside a code execution container. Tool results from programmatic calls are not added to Claude's context window, only the final code output is. They report up to 98.7% token savings in some workflows.
So the point here is: MCP isn't just valuable for the centralization, auth, and telemetry story the author laid out (which I fully agree with). The protocol itself, specifically its structured schema capabilities, directly enables more efficient and reliable agentic workflows. That's a concrete technical advantage that CLIs simply don't offer, and it's one more reason MCP will stick around.
Long live MCP indeed.
Smolagents makes use of this and handles tool output as objects (e.g. dict). Is this what you are thinking about?
Details in a blog post here: https://huggingface.co/blog/llchahn/ai-agents-output-schema
This eliminates the "print-and-inspect" pattern where CodeAct agents call tools just to discover what data they get back. Instead of multi-step exploration, agents can write complete, precise programs from the start.
What's new: Tools declare their output schemas upfront
What's better: Agents plan complete execution paths instead of reactive discovery
Now supported in Hugging Face smolagents.