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 covered. The description adds real behavioral context beyond them by disclosing the asynchronous execution model (queues a hosted job) and the follow-up retrieval path via get_job.

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 short sentences with zero filler, front-loading the core action and then the async follow-up. 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?

There is no output schema, and the description correctly points to get_job for results, which covers the return path. However, for a 6-required-parameter mutation with only 33% schema coverage, the optimistic-concurrency semantics (expectedRevision) and the meaning of targetEventId remain entirely unaddressed.

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% (requestId and workspaceToken are documented), leaving projectId, expectedRevision, idempotencyKey, and targetEventId unexplained. The description adds no parameter meaning at all, so it fails to compensate for the coverage gap.

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 ("Reverse") and resource ("recorded reversible project mutation"), which is materially more precise than the tautological title. It does not, however, distinguish itself from the sibling undo_transformation, which an agent must choose between.

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 gives a useful follow-up instruction ("use get_job to retrieve its result"), which is genuine operational guidance. But it offers no when-to-use criteria versus undo_transformation or any prerequisite/exclusion conditions.

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