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

Beyond annotations (which only say non-destructive, idempotent, non-open-world), the description discloses that the call is asynchronous and returns immediately with a job handle, that the snapshot is immutable, and what the snapshot records (geometry, layers, warnings, persistence source). This is exactly the behavioral context the annotations cannot carry.

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 action, then the return contract, the snapshot semantics, and finally the sibling exclusion. Every sentence is load-bearing, though the snapshot-contents sentence is dense enough that it borders on over-packing for a short description.

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?

Covers the async handoff, the follow-up tool, and the alternative tools, and an output schema exists so return-value detail need not be duplicated here. Nothing an agent needs to invoke this correctly and consume the result is missing.

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?

The description adds no per-parameter guidance — nothing about timestamps batching, scale, image format, or composition selection — so the schema's own rich field descriptions do all the work. The only implied mapping is the 'persisted, inline, or session scratch' phrase touching on composition/session_id semantics. With ~50% declared coverage, this is an unambitious but adequate baseline.

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+resource ('queue durable still-frame evidence') plus the intent ('for layout/copy judgment'), and explicitly separates itself from preview_clip/preview_component for animation. An agent can route between the three preview tools 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?

Gives an explicit when-to-use ('layout/copy judgment'), an explicit when-not ('A still cannot prove motion'), and names the correct alternatives (preview_clip, preview_component). It also tells the agent the required follow-up call (wait_job with kind/id), so the workflow is not left to inference.

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