scenes

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

With no annotations provided, the description carries the full burden and does a good job: it discloses that detect_scenes reads every source, reports cuts in timeline time, writes markers, and performs splits. It also reveals the backend dependency on PySceneDetect vs ffmpeg and that the result names which backend answered, though it does not describe the exact return shape or whether splitting is destructive/reversible.

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 description is dense and front-loads 'Shot boundaries,' then packs the three actions plus backend behavior into a compact format. The inline argument list inside the first sentence makes parsing slightly harder, but every clause contributes useful information.

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 multi-action tool with no output schema and no annotations, the description leaves gaps: it does not describe the return value structure for detect_scenes, and it does not spell out the arguments required for scenes_to_markers and scenes_split. The action enum and filepath are covered, but an agent could still be unsure how to invoke two of the three actions correctly.

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?

The schema only describes args as a generic object, so the description adds substantial meaning by enumerating filepath, clip_name, backend, threshold, and min_scene_len with optionality and a default. However, it does not specify which arguments apply to scenes_to_markers and scenes_split, so it is not fully complete.

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?

The description clearly identifies the tool's domain with 'Shot boundaries' and names three distinct actions with specific outcomes: detect_scenes reports cuts, scenes_to_markers writes markers, and scenes_split cuts clips. This differentiates it from sibling tools like 'mark' and 'edit' by giving each action a specific verb and resource.

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?

The description provides clear context by laying out the three operations and their sequential relationship: first detect, then optionally write markers or split. It does not explicitly name sibling alternatives or state when not to use this tool, so it falls just short of giving full exclusion guidance.

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