preview_keyframe_selection

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

With no annotations, the description carries the full burden. '幀級精確' and '本地完整視頻場景' hint that it works frame-accurately on a local video without remote IO, but it never says whether anything is mutated, whether this is a pure read, or what resources it consumes.

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?

A single short sentence with no filler and the key qualifier front-loaded. The brevity costs clarity (unexplained jargon like 右邊界截斷), but nothing is wasted.

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?

An output schema exists, so return values need not be explained. However, for a 5-parameter tool with zero schema documentation, no annotations, and an ambiguous preview/mutation status, the description leaves too much unknown for a correct invocation.

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 0% across 5 parameters (fps, duration, min_gap_sec, scene_points, max_window_sec) and the description names none of them. '幀級精確' and '右邊界' only indirectly gesture at fps and the window/gap parameters, so the agent has essentially no parameter meaning beyond bare names.

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?

It states a verb (預覽/preview) and an object (右邊界截斷結果/right-boundary truncation result), but 'truncation result' never connects explicitly to keyframe selection, which only appears in the tool name. Against the sibling preview_keyframe_selection_seek there is no differentiation at all, leaving the agent to guess what is actually being previewed.

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?

No indication of when to call this versus preview_keyframe_selection_seek or read_frame_at, and no prerequisites or exclusions. The word 預覽 implies a dry-run/preview usage, but nothing routes the agent between the near-identical siblings.

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