launcher_rollback

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the agent knows it is a non-destructive write, but the description adds little beyond "go back." Critically, it never reveals the two-phase flow implied by the schema's owner_approved field — that omitting approval yields only a preview — so an agent may believe a bare call has already changed the device.

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?

One short sentence with the default front-loaded in parentheses; nothing is padded. The size is appropriate, though the brevity comes at the cost of the missing semantics noted elsewhere.

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 launcher-mutating tool with a preview/approval gate, an undescribed `to` parameter, and no output schema, the description leaves the agent without the facts needed to call it safely. It should explain what a rollback target looks like and that the unapproved call only previews.

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 67%; device and owner_approved are documented in-schema, but `to` has no schema description at all. The description partially compensates by stating the default for `to` (the previous screen), yet it never says what form the value takes — a history index, a snapshot name, or an ID.

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?

"Go back to an earlier home screen" gives a verb (rollback) and a resource (home screen layout/state), so the general intent is graspable. But "home screen" is left ambiguous — it could mean a saved layout, a snapshot, or a history entry — and no sibling is referenced despite launcher_history, launcher_preview, and undo all orbiting the same space.

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?

The only guidance is the default (previous state); there is no statement of when to prefer this over undo, restore_everything, or applying a variant from launcher_history. An agent has to guess whether a history entry must exist first or whether the tool discovers prior states itself.

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