The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

MCP BlogTools

Tool Annotations as Risk Vocabulary: What Hints Can and Can't Do

03.16

MCP tool annotations were introduced nearly a year ago as a way for servers to describe the behavior of their tools — whether they’re read-only, destructive, idempotent, or reach outside their…

Read at MCP Blog ↗

One letter a week, starting soon.

Latest

Tool Annotations as Risk Vocabulary: What Hints Can and Can't Do

More from MCP Blog on Accept All

ToolsMCP Apps - Bringing UI Capabilities To MCP Clients MCP Blog

ToolsJanuary MCP Core Maintainer Update MCP Blog

ToolsOne Year of MCP: November 2025 Spec Release MCP Blog

ToolsMCP Apps: Extending servers with interactive user interfaces MCP Blog

ToolsServer Instructions: Giving LLMs a user manual for your server MCP Blog

ToolsEvolving OAuth Client Registration in the Model Context Protocol MCP Blog