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

Beyond the annotations, it discloses that this is an asynchronous queued job, that it is idempotent per immutable snapshot, and that billing only fires on the guarded success terminal. It also notes the snapshot/isolation semantics (judging the authored target) and the 404-not-fallthrough behavior for stale ids, which are non-obvious operational traits.

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?

Dense but front-loaded: purpose first, then the polling/fix loop, then idempotency and billing caveats. Every clause carries information, though the packed sentence structure requires careful parsing.

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 nested-body, async, write-capable tool with an output schema and annotations, the description supplies the missing operational context: the job/polling model, the returned artifact set, idempotency, and billing trigger. Nothing needed to invoke it correctly is absent.

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?

With schema coverage at 50%, the description does add meaning for body.composition (optional, absent ⇒ ACTIVE), but that is largely restated in the schema itself. It does not clarify the session_id vs compositionId precedence or the purpose of brandContext/editorialIntent, leaving part of the coverage gap unaddressed.

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 opens with a precise verb+resource ('Queue the durable server-side judge') and immediately specifies the graded dimensions (editorial/spatial/brand/caption) and the target snapshot. An agent can distinguish it from apply_composition, compose, and validate_composition without opening any 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?

It gives a clear workflow: queue here, then poll wait_job(kind="verify", id=jobId), then fix the lowest criterion via apply_composition and re-score. It does not, however, explicitly state when to prefer this over siblings like validate_composition or compose_verify, so the routing is implied rather than enumerated.

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