restore_everything

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description still adds real value: it discloses the newest-first ordering and two side effects (restoring the home screen, removing Shape) that an agent could not infer. It omits that omitting `owner_approved` yields only a preview, a notable behavioral gate, which keeps it from a 5.

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 compact sentence with the core action front-loaded and no filler. The trailing parenthetical is dense but rewards reading, though its undefined term "Shape" costs some clarity.

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 destructive bulk-undo tool with no output schema, the description covers scope, ordering, and side effects reasonably well. It leaves the safety workflow (preview-then-approve) undocumented in prose and leaves "Shape" unexplained, gaps an agent must fill from the schema alone.

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 100%, and both `device` and `owner_approved` are fully explained in the schema itself. The description adds no additional parameter meaning (e.g., how the preview output differs from the applied result), so the baseline of 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?

"Undo every change, newest first" gives a specific verb plus a clear scope and ordering, and the breadth ("every") implicitly separates it from the sibling `undo`. The parenthetical, however, introduces undefined jargon ("Shape") that an agent cannot resolve, so the operation's full effect is only partly clear.

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 the scope word "every" versus the narrower sibling `undo`, but the description never states when to choose this over `undo` or `launcher_rollback`. There is also no mention of the preview-only default behavior that the schema implies via `owner_approved`.

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