Apply one approved Ghost change set

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, and the description adds substantial behavior beyond them: a re-read/preflight step, mandatory hash and scope validation, a Ghost revision saved for every edit, readback verification, and fail-fast termination after the first remote failure. The fail-fast detail is especially valuable because it implies earlier edits in the batch are already committed, which the annotations do not convey.

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 dense sentence, front-loaded with the core action and then the guards, with no filler. It is grammatically heavy (six chained clauses) but each clause conveys a distinct operational fact, so little 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, up-to-25-item batch tool with an output schema present, the description covers the essential context: approval gating, hash binding, revision creation, readback and failure behavior. It does not address whether prior successful edits are rolled back on later failure, nor the concurrency meaning of target.updated_at, which is the main remaining gap.

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 0% on four parameters with deep nesting, so the description carries real burden. It usefully clarifies that preview_hash must be site-bound and exactly match the preview, and that scopes must match exactly, but it never explains the shape or semantics of the 'changes' array (target/operation/updated_at concurrency token) or 'user_confirmed', which the schema names only structurally.

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?

The description gives a specific verb+resource ('Apply one approved Ghost change set') and enumerates the exact execution semantics: re-read/preflight the previewed batch, require the preview hash, save revisions, verify readback. It implicitly ties to the preview_changes sibling via 'the exact previewed batch', but it never names or contrasts that sibling, so an agent must infer the pairing.

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?

Preconditions are stated concretely: the change set must already be approved, must supply a site-bound preview hash, and must match exact approval scopes. That tells the agent when the call is valid. It does not state when NOT to use it or point to an alternative (e.g. re-run preview_changes after a mismatch), leaving one gap.

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