undo_live

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

Annotations already flag destructiveHint=true, readOnly=false, and non-idempotent, so the safety profile is covered. The description adds genuine context: the ordering semantics ('newest first') and the exact payload that gets reverted. It stops short of saying whether an undo is itself reversible or what happens when no live edits exist, so a 4 rather than 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?

Two sentences, zero filler. The action and scope are front-loaded, and the routing guidance to alternatives is packed into the second sentence.

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 need no explanation, and annotations carry the safety profile. Scope, ordering, and sibling routing are all present; the only minor gap is error/no-op behavior when there is nothing left to undo.

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 100% and the single 'count' parameter is fully documented in the schema. The description only reinforces the ordering ('newest first'), which implies how count selects edits but adds no format or edge-case detail beyond the schema baseline.

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) plus the resource (latest instant/live edits), scopes it to edits made by update_key, and enumerates what reverts (titles, images, settings). This distinguishes it cleanly from update_key, discard_changes, and restore_backup without opening a schema.

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?

Explicitly names the alternatives (discard_changes, restore_backup) and the condition that selects them ('staged changes and applied plans'), leaving the agent no inference work to pick the right tool.

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