Undo Last Change

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

Annotations declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description adds real context beyond them: the action is a *proposal* requiring editor approval, the mechanism is native Undo, and the tool self-limits to the most recent edit. It does not say what happens to edits after the proposal is approved or rejected, but the approval gate is the crucial behavioral detail an agent needs.

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?

Three short sentences, each earning its place: what it does, what it excludes, what it requires. The primary action is front-loaded with no filler.

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?

An output schema exists, so return values needn't be described, and annotations cover the safety profile. The description still conveys the mechanism and approval gate, but it leaves open what a proposal looks like downstream or how a failed undo is surfaced — minor gaps for a one-parameter 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?

There is one parameter (request_id) and the schema documents it at 100% coverage, including the retry rule about reusing the same ID. The description adds nothing about it, but the schema already carries the full burden, 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 and resource: 'Propose undoing the most recent VoxelFlow edit using native Undo.' The scope limit ('most recent', 'native Undo') separates it from anything else in the sibling list, though no sibling alternative is named because none offers undo.

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?

Gives both a when ('most recent VoxelFlow edit') and a when-not ('Refuses to undo unrelated artist edits'), plus the prerequisite 'Requires editor approval.' Clear context, but it never names an alternative path for edits outside its scope, so it stops short of a 5.

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