MCP blog: Tool annotations

Creator not supplied; see original source.

MCP blog post on tool annotations such as read-only and destructive hints, and how far clients should trust them.

Level: Intermediate
Models
Category: Jailbreaking and red teaming
Tags: safety-evals, safety-security-interpretability
Source date: date not stated
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok
Prerequisites: source
Subcategory: safety and alignment evals
Region: unknown
Original language: en
Access: free
Resource reuse: unknown: Not supplied; no reuse grant asserted. Facet definitions
Verification basis: Supplier-reported live check; no independent HTTP verification by this site.
Access evidence: Supplier-approved free inventory; not independently verified by this site.
Source domain: Safety, security & interpretability
Source subdomain: safety evals
Supplier region label: Global

Summary in our own words. Rights remain with the original creator. Credit and correction policy.