Clip a long video

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

Far exceeds what the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) convey: it discloses the cost model (a ~7-credit hold settled to exact transcription+encode cost, plus a separate per-clip vision-call event), the refund-on-failure behaviour, the mid-run truncation flag, the burn-in-caption default, and the fact that timing is sentence-anchored and not frame-accurate. That is exactly the kind of side-effect/billing disclosure an agent needs before calling a non-idempotent, paid operation.

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?

It is front-loaded with the core action and largely structured around input handling, reframe mechanics, cost, and return shape. But it is roughly 450 words with heavy ALL-CAPS emphasis and repeats the captions default/logic that the schema already carries, so several sentences do not fully earn their place.

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 compensates fully: it enumerates the returned clips[] fields (served mp4 URL, title, hook, caption, 0-100 score, timecode), the diagnostic fields (reframedToSubject, reframeWhy, captionsBurned, captionNote, truncated), and the failure/refund path. For a paid, multi-stage generation tool, an agent has everything needed to call it and interpret the result.

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 100%, so the baseline is 3; the description earns above it by tying parameters to behaviour the schema doesn't state — one small vision call per clip (linking count to cost), captions:false for clean footage, and the read-back fields captionsBurned/captionNote that signal a clip may be delivered bare. The aspectRatio reframe note is also explained at a level the schema's short enum description does not reach.

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 precise verb+resource+scope: 'Cut ONE long video into several RANKED, ready-to-post short clips', with the source genres enumerated (podcast, webinar, interview, conference talk). It implicitly distinguishes itself from generate_video ('no video model renders anything') and from single-output editors by stressing it returns clips[], not one video.

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 rich when-to-use context (long-form → Reels/Shorts/TikTok) and explicit when-not (no TikTok/Instagram/Facebook links, no age-restricted/private/live sources, min ~15s, under ~600MB, first ~40 min only), plus the fallback 'ask for a direct file or an upload rather than retrying'. It stops short of naming sibling tools like reframe_video or edit_video as the alternative for adjacent jobs, staying at clear-context rather than full routing.

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