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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower, and the description still adds the crucial non-obvious trait that this queues a hosted job rather than completing synchronously. It does not explain what happens on revision mismatch or how retries interact with idempotencyKey.

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, with the state change front-loaded and the async retrieval instruction second. Every clause earns its place.

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 an async, 6-required-parameter mutation with no output schema and low schema coverage, the description covers the job-queue model but leaves the concurrency/idempotency contract and parameter meanings undocumented, so an agent could easily supply a stale revision or a reused key.

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 only 33% (2 of 6 params documented), so the description must compensate and does not: it never explains expectedRevision's optimistic-concurrency role, idempotencyKey's retry semantics, or projectId, and only alludes to runId via 'one applied transformation run'.

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 ('mark ... undone') and resource ('one applied transformation run') plus the side effect ('restore its derived variable'), so the agent knows exactly what changes. It does not, however, contrast itself with the sibling undo_change, which an agent must disambiguate against.

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?

It tells the agent the follow-up step ('use get_job to retrieve its result'), which is real operational guidance for an async tool. It gives no when-to-use versus undo_change, no prerequisites (workspace capability, revision), and no exclusions.

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