fablecut_highlights

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

With no annotations, the description carries the full behavioral burden and does so richly: it discloses the sampling method (twice a second, half-second scoring on movement/sound/picture), that existing cuts are never crossed, that the source timeline is left untouched and a version is saved first, that output lands on V1 of a new opened sequence, and that ffmpeg must be on PATH. This is exactly the operational context an agent needs before invoking.

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 a dense, fairly long paragraph, but the core action is front-loaded and each sentence contributes (sampling, scoring, cut avoidance, defaults, output placement, follow-ups, prerequisite). A few clauses (story order, linked sound, timeline untouched) could be trimmed, but nothing is 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?

For a six-parameter tool with no output schema and no annotations, the description covers inputs, defaults, side effects, output shape (reply lists source, times, and why each moment was picked), and prerequisites. An agent could invoke this correctly without further information.

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 already 100%, so the baseline is 3; the description earns above that by explaining derived behavior — shot defaults to duration/8 clamped to 1.5–4 s, duration defaults to 30 s, and aspect changes the new sequence's shape and triggers fablecut_reframe. It adds real meaning beyond the schema's own parameter text.

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-and-resource statement — cutting the best moments of long footage into a short edit — and illustrates it with real cases (30 s reel from a 20-minute vlog, a match, B-roll). It clearly names what it consumes (timeline clips, clipIds, or mediaIds) and how it differs from fablecut_beats and fablecut_reframe, which it frames as follow-up steps.

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?

It states the primary default (every video clip on the open timeline) and the two alternative input modes (clipIds, mediaIds), and it routes the agent onward to fablecut_reframe for reframing and fablecut_beats for beat-cutting. There is no explicit 'don't use this for X' exclusion, but the context for use is unambiguous.

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