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

Annotations already declare destructiveHint=true and idempotentHint=false; the description reinforces this with the session-scoped, single-step semantics that explain why it is non-idempotent and how far its reach extends. It does not state what happens when the undo stack is empty (error vs. no-op), which is the one behavioral gap left.

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?

Two tight clauses, no filler; the scope constraint is front-loaded in capitals and the repeatability rule follows immediately. Every phrase carries operational meaning.

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?

For a two-parameter tool with full schema coverage, complete annotations, and no output schema, the description covers scope, mechanics, and limits. Missing only the empty-history edge case and any indication of what the call returns on success.

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 100% and both parameters (token, projectId) are documented inline with useful guidance about what they identify. The description adds nothing parameter-specific, so the baseline 3 applies.

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 (reverts) and a precisely scoped resource: the most recent edit made by THIS agent session to the project. The scope qualifier separates it cleanly from any manual/other-tab editing path in a large sibling list dominated by direct manipulation tools like move_clips and remove_clips.

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?

"one step per call; repeat to go further" tells the agent exactly how to escalate, and "Cannot revert other tabs' or the user's edits" is an explicit when-not condition. It stops short of naming the alternative recovery path (e.g. re-issuing the inverse edit tool) when undo is unavailable, so not quite a 5.

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