Stage Edit Undo

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

With no annotations, the description carries the full burden and does well: it discloses the page reply shape {undone, undo_depth}, the emitted event `undo {objects, lights, materials, depth}`, and the conditional behavior ('when there was something to undo'). It does not cover the nothing-to-undo case explicitly, permissions, or whether history depth is bounded.

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 front-loaded sentences with no filler; the operation and scope come first, followed by reply/event details. The reply and emit payloads partially duplicate the output schema, but they are compact and informative rather than wasteful.

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 one-parameter undo tool with an output schema, the definition covers what is undone, the scope of attribution, and the emitted event, which is enough to call it correctly. The remaining gap is the unspecified `scene` value and the no-op case, both minor against an existing output schema.

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?

The single required parameter `scene` has 0% schema description coverage, and the description never explains what it accepts (scene name vs. id) or what happens if it is omitted. Since schema coverage is below 50%, the description was expected to compensate and does not.

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 the resource it acts on (the last edit on the page), and enumerates the edit types covered (move, light, material) plus the attribution scope ('whoever made it'). It is clear what the tool does, though it does not explicitly distinguish itself from the sibling `undo` tool, which is a real ambiguity given a generic undo exists.

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?

Usage is implied by 'undo the last edit on the page' and the parenthetical page command mapping, but there is no explicit 'use this instead of X when Y' guidance, nor any statement of when not to use it (e.g., versus the sibling `undo`). The agent must infer the selection rule.

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