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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real context by disclosing the output modality (contact sheet, spectrogram under each row, text summary of loudness and masking) and the input constraint that durationSeconds must be positive. It stops short of stating frame count, resolution, or cost, which would have made it a 5.

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?

Four short sentences, front-loaded with the core action and the output nature, with no filler. The final imperative 'read the pixels' is terse but informative about what to do with the result; slightly compressed phrasing costs it a point.

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?

With no output schema, the description carries the burden of describing the return, and it does: a contact sheet plus optional per-row sound strips and a summary. For a read-only preview tool with annotations covering safety, this is nearly sufficient; only frame density and the meaning of startSeconds remain unstated.

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 coverage is 50%: audio is exhaustively documented in the schema, while startSeconds and durationSeconds have no schema description. The description adds one genuine constraint not in the schema ('durationSeconds is positive') and clarifies audio's mix/tracks effect, but startSeconds is never explained beyond the vague 'source-time window', so it only partially compensates 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 concrete verb and resource: it returns a contact sheet of a source-time window in the composed timeline. An agent can infer the distinction from preview_frame (single frame) and preview_timeline (whole timeline) from the 'window'/'contact sheet' framing, but no sibling is named explicitly, so differentiation is inferential rather than stated.

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?

'Use for motion and for lining sounds up with the frames' gives a positive use case, and the audio argument suggests when to enable the spectrogram. However, it never says when NOT to use this versus preview_frame or preview_timeline, nor what prerequisites exist, so guidance is implied rather than explicit.

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