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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the details an agent actually needs: current state is snapshotted first (safety backup plus a history version) so the operation is undoable, live site is untouched, and unpublished draft work is replaced. That is exactly the 'what gets destroyed / what is recoverable' context annotations cannot carry.

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?

Three sentences, zero waste, and the single most important constraint (DRAFT only, never live) is front-loaded in the first line. Parentheticals are used to pack alternatives and provenance rather than adding separate sentences.

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, non-idempotent mutation with no output schema, the description covers recoverability, blast radius per scope, parameter provenance, and the required user confirmation. Nothing an agent needs in order to call this safely is missing.

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%, so 3 is the baseline, but the description goes further by explaining the effect of each enum value (site = every file and page, page = one page) and by tying pageNodeId and revisionId to their upstream source in list_site_history. It stops short of noting that id is optional/inferred, which keeps it from a 5.

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+resource ('Put a past version back') and immediately pins the target scope: the DRAFT, never the live site. It explicitly separates itself from publish_site, so an agent can distinguish restore-from-history versus go-live without opening either 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?

Gives concrete when-to-use branches: scope 'site' (default) for every file and page versus 'page' for one page, and names the prerequisite source for pageNodeId/revisionId (list_site_history). It also states an explicit gating condition — confirm with the user first — which is real usage guidance, not filler.

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