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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: 'Atomically' discloses all-or-nothing semantics, the parenthetical enumerates the exact scope of mutation, and 'the last' implies only the most recent apply is revertible — a meaningful non-idempotency constraint.

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 sentence, front-loaded with the atomic-restore action and the target, with the scope enumeration in a compact parenthetical. No filler or restated title.

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 mutation with no output schema, the description covers what gets restored and that the operation is atomic, and annotations carry the safety signals. It omits the failure mode when no prior apply exists and whether the revert itself can be undone, which keeps it short of full completeness.

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%, so site, context, and guestToken are all documented in the schema itself. The description adds no parameter-level detail (e.g., which site scope the revert targets), so the baseline 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?

States a specific verb (restore/revert) and precisely scopes the resource: everything the last adapt_site_apply wrote, with an enumeration of the artifacts (fragments, menu doc, index, member configs, routes). This clearly distinguishes it from sibling adapt_site_apply and from the narrower revert_change.

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 phrase 'the last adapt_site_apply' implies the usage context (undo the most recent apply), but the description never explicitly states when to use this versus revert_change, discard_drafts, or what happens if no prior apply exists. Usage is inferable but not spelled out.

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