Model Context Protocol10 min read
Tool Annotations as Risk Vocabulary: What Hints Can and Can't Do
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 local environment.
By Ola Hungerford (Maintainer), Sam Morrow (GitHub), Luca Chang (AWS)Model Context Protocol (MCP) Blog

Read the full story
Originally published by Model Context Protocol (MCP) Blog on Mar 16, 2026.
Comments
Sign in to join the discussion.