Reliable Mutations

Rule

Make a change in one atomic call when the action supports it, then verify the persisted end state and report concrete proof (counts/ids). Never drive a multi-step change by looping many small writes, and never report success from a tool ✓ alone.

Why

Hosted foreground agent runs have a short soft budget so they can hand off cleanly under synchronous serverless walls. Durable background runs get a much longer budget, but they still should not rely on loops of many small writes: continuations can retry the same intent and leave partial state if each item is committed separately. One atomic call commits or fails as a unit; verification turns a hopeful ✓ into a fact.

How