Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotent, so safety is covered. The description adds a genuinely non-obvious trait: later work is preserved, meaning this is not a truncating rollback. It stops short of stating whether the undo is itself reversible or how conflicts with later edits resolve.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with zero filler; the exclusion constraint and the preservation semantics are both front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations carry the safety profile and no output schema exists, but for a destructive mutation the definition says nothing about confirmation, reversibility, or failure modes when the act is already superseded. Adequate but with clear gaps for a 5-parameter destructive tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60% and the schema text already repeats "pass act or turn_id" per property, so the description's exclusion rule is partly redundant. It adds nothing about `document`, `agent`, or `operation_id`, leaving the idempotency-retry parameter undocumented in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (undo) and resource (one act or one turn) with an explicit mutual-exclusion constraint, so the operation is unambiguous. It doesn't name a sibling tool or explain how it differs from 'edit', which keeps it short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"act or turn_id, not both" is a concrete selection rule between two competing parameters, and "preserving later work" tells the agent this is a surgical removal rather than a rollback-to-point. No explicit when-not-use or alternative tool routing is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.