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

Annotations already declare readOnlyHint/destructiveHint, and the description adds substantial behavior beyond them: results arrive as actual images, multiple frames are merged into a numbered contact sheet, sampling is capped at 12 frames, source-mode times are in source seconds while timeline-mode times are in timeline seconds, and each timeline frame is the top visible clip under the playhead. The max-12 and playhead semantics are non-obvious and materially affect invocation.

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?

The core is front-loaded ('SEE the footage') and the mode/purpose/usage sentences each earn their place. The trailing boilerplate list 'response_detail (summary|compact|full), fields (dotted paths), cursor (next page) — see the server instructions' reads as template residue that belongs in the parameter layer rather than the 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?

For a 10-parameter, no-output-schema tool the description appropriately explains the return shape (image frames / numbered contact sheet) and core timing semantics. It is weakened by leaving job_id undocumented, not clarifying the sheet flag, and deferring cursor pagination to server instructions, so an agent cannot fully resolve every parameter from the definition alone.

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 0% schema description coverage across 10 parameters, the description carries the burden and explains the important ones: asset_id selects source vs timeline mode, times gives exact moments, start_s/end_s/count sample a range with a max of 12, and it names response_detail (summary|compact|full), fields, and cursor. However job_id is never explained and sheet is only obliquely implied by 'contact sheet', leaving real gaps.

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?

Opens with a concrete verb+resource ('SEE the footage: decoded frames come back as an image') and immediately splits the tool into two distinct modes: asset_id for a single clip's source versus omitting it for the timeline. A reading agent can distinguish this from screen_look and the ws_*/arsaze_* siblings purely from the text.

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 explicit when-to-use cases ('check who is on camera, framing, a bad frame, which angle is which'), an explicit when-not ('Check already_noted first: if another agent wrote down what's there, you may not need to look'), and a follow-up action (save findings with media_note). Nothing about routing 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.