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

Annotations already declare this a safe, non-destructive read, so the description's value is in the extra operational facts it supplies: output is PNG, up to 8 frames per call, batching is faster than one call each, and frames draw down the workspace's monthly allowance. The quota/cost disclosure is genuinely useful behavior an agent cannot get from annotations. It stops short of saying how frames are returned (inline vs. URL) or what resolution is used.

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 tight sentences, front-loaded with what is rendered and in what format, followed by the use case and the cost caveat. Every clause carries information; there is no restatement of the title or filler.

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, so the description must stand in for return shape, and it identifies PNG plus the 8-frame cap, which covers the essentials for a preview tool. Gaps remain on time/times semantics and on where the rendered images go after the call, but for a low-risk read operation with annotations covering the safety profile this is close to sufficient.

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 50%: height and projectId carry their own descriptions, while time and times are bare. The description partially compensates by implying times accepts up to 8 values in one call, but it never explains the relationship between the singular time and the plural times (mutually exclusive? one wins?) or their unit/format. That ambiguity is the main thing an agent needs and does not get.

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 and resource ('Render exactly what the export will look like at timeline times') and names the output format and batch limit, so the agent knows it produces preview frames rather than a final file. It does not, however, distinguish itself from the sibling view_media_frames, which an agent could easily confuse with it.

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?

Provides an implied when-to-use ('Use this to check your edits visually'), which is clear enough context for the preview use case. It gives no when-not guidance and never mentions view_media_frames or export_video as alternatives, so routing between the three visually similar tools is left to inference.

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