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

Annotations already declare the safety profile (readOnlyHint=false, idempotentHint=true), and the description adds real behavioral context: async job semantics, that failures 'land on the job terminal with sanitized author-fixable messages,' and idempotency 'per immutable render key.' It stops short of auth/rate-limit or timing details.

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?

Front-loaded with the core verb and async contract, and every sentence carries non-obvious information (slot binding, failure terminal, idempotency). It is dense and slightly long, but not padded.

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?

An output schema exists, so return values need not be explained, and the description does cover input semantics, async flow, failure modes, and idempotency. It is complete for a job-queueing tool, with only sibling differentiation left implicit.

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 50% schema coverage, the description compensates by explaining `body.componentId` selects the component, `body.params` renders props, and manifest slots bind to `assets` and 'never params' — a distinction the schema does not make. It does not cover the numeric fps/width/height/durationInFrames params, which the schema already documents.

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 ('Queue a typed preview artifact') and resource ('ONE org-installed component'), and its 'preview ... component' framing distinguishes it from sibling preview tools like preview_card, preview_clip, and preview_frame.

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 describes the async workflow — 'returns a jobId immediately; then wait_job(kind="preview", id=jobId)' — so the agent knows the required follow-up call. It does not, however, name when to prefer it over the sibling preview_* tools or state exclusions.

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