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

Annotations already flag destructive/not-idempotent, and the description adds genuinely new behavior beyond them: current state is saved first so the rollback itself is reversible, files created after the snapshot are left untouched, and DB dumps are excluded. These are exactly the side-effect details an agent needs before invoking a destructive tool.

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 short sentences, all load-bearing: the action, the reversibility guarantee, and the two exclusion rules. The scope statement is front-loaded and nothing is wasted.

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 reversibility, scope, and exclusion rules, which is most of what an agent needs. It leaves the multi-server 'server' parameter and the approval_id re-call flow to the schema, a minor gap rather than a blocking one.

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 60%, so the schema already documents 'why', 'server', and 'approval_id'. The description only adds meaning for 'paths' (partial selection) and hints at the approval flow; it says nothing about 'server' or 'approval_id' beyond what the schema provides. Baseline 3 is appropriate.

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 ('write ... back') on a specific resource (a snapshot's files) and scopes it ('all of it, or only some paths'). It is clearly distinguishable from the sibling 'snapshot' (create) and from 'run', which it explicitly names as the alternative for database dumps.

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 a concrete when-not rule with the alternative tool: 'database dumps are not loaded (use run)'. It also implies the partial-vs-full choice via the 'paths' param. It stops short of routing against the other undo-style siblings (cf_undo, content_undo, redirects_undo), so not a full 5.

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