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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is largely structured. The description adds genuine value by stating the blast radius ('No provider work, content publication or outcome claim'), which tells the agent this is a bookkeeping-only mutation. However it omits the version-conflict behavior implied by expectedVersion, which is the main risk an agent needs to know about.

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 tight sentences with the action front-loaded and the scope disclaimer second. Nothing is padded, though the 'using stateVersion and idempotencyKey' clause actively introduces a naming error rather than earning 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 a versioned, idempotency-keyed mutation with no output schema, the description leaves key gaps: what happens on a version mismatch, what state the run must be in, and what the caller receives. The mismatched parameter name further reduces confidence that the agent can invoke it correctly.

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%, so the description must carry the load for four parameters, but it only nods at two and does so inaccurately: it says 'stateVersion' while the schema requires 'expectedVersion'. runId and workspace are never explained, and no semantics (dedupe key format, concurrency check, workspace scoping) are added over the raw schema.

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 names a specific verb ('Restore') and target ('a reviewed recorded run to the review queue'), which clearly separates it from the sibling read tools like read_latest_answer_reviews and the forward-looking review_answer_evidence. It stops short of explicitly naming the inverse operation it pairs with, but the intent is unambiguous.

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?

Usage is only implied: the agent must infer that this applies to a run that was already reviewed and needs to be placed back into the queue. No alternative (e.g. review_answer_evidence) is named and no precondition or when-not guidance is given, though the negative scope sentence does bound what the call will not trigger.

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