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

Annotations already declare non-readOnly, idempotent, non-destructive, closed-world. The description adds genuinely new behavioral context: this queues an asynchronous hosted job whose result must be fetched via get_job, the change is reversible and carries recorded provenance, and approval must be real. That exceeds what the annotations convey, though it doesn't cover failure modes or job lifetime.

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 tight sentences, front-loaded with what the tool does, then the async/result-retrieval behavior, then the approval precondition. No filler; each sentence 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 a 9-parameter mutation with no output schema, the description usefully routes the agent to get_job for results and states the approval requirement. However, with 22% parameter description coverage and no explanation of expectedRevision/idempotencyKey semantics, it is not complete enough for confident invocation.

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 22% across 9 required parameters, and the description clarifies only the approval/approval-fabrication aspect and the wave scope. Key parameters such as expectedRevision (concurrency control), idempotencyKey, runId, recipeId, and workspaceToken receive no added meaning in the description, 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 (apply), resource (transformation), and scope (one workspace wave), and adds distinguishing qualifiers 'approved' and 'reversible provenance' that separate it from propose_transformation and review_transformation. An agent can tell what it does without opening the schema.

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?

Explicitly states the precondition ('obtain actual user approval before calling'), names the follow-up tool for retrieving results ('use get_job'), and warns against fabrication. That is clear when-to-use, how-to-continue, and what-not-to-do guidance.

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