Revert asset edits

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

Annotations already declare destructiveHint=true, but the description goes further by specifying exactly what is destroyed -- 'deletes all edit records for the assets' -- and clarifying the scope limit to non-destructive display edits only. It also discloses the return shape (reverted/failed counts), which helps the agent verify partial failure.

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?

Front-loaded with purpose and side effect before the Google-style Args/Returns blocks, and every sentence carries information. The Args section slightly duplicates the prose mutual-exclusion line, costing a little redundancy but no real ambiguity.

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 destructive mutation, the description covers purpose, the undo relationship to rotate_assets, the selector exclusivity, and the side effect. Remaining gaps are minor: no behavior defined when both selectors are omitted, and no note on whether reverted edits can be re-applied.

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 description coverage is 0%, so the description must carry the burden, and it does: both parameters are explained and their mutual exclusivity is stated, which the schema does not encode. It does not warn that album_id defaults to an empty string rather than null, leaving ambiguity about what happens with neither argument supplied.

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 ('Remove all non-destructive edits ... from assets') and enumerates the exact edit types affected (rotation, crop, mirror), plus the outcome ('restoring original appearance'). It also implicitly contrasts with the rotate_assets sibling by naming it as the operation being undone.

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 an explicit trigger: 'Use this to undo rotate_assets or any other display transforms,' which routes the agent from the transform-producing sibling to this one. It adds the EITHER/OR constraint on the two selectors. It does not say when NOT to use it (e.g. versus deleting the asset) or what happens if both are omitted.

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