capcut_find_visual_scenes

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

No annotations are present, so the description must carry the behavioral burden. 'Search and retrieve' and 'timestamped scenes' do suggest a non-mutating read operation and hint at the return value, but there is no explicit statement that the draft is not modified, that an understanding map must pre-exist, or how missing-map failures are handled.

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 well-structured sentence front-loads the primary verb and resource, then supplies concrete examples. There is no filler, no redundant restatement of the tool name, and no unnecessary detail.

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 only two simple parameters and no nested objects, this is a fairly light tool, but there is no output schema, so the description should carry return semantics. It does mention 'timestamped scenes' but omits the prerequisite that the draft's video understanding map must already be built, which is relevant given the sibling capcut_analyze_video_understanding.

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 50%: the query parameter is already described, but the required draft parameter has no schema description. The tool description adds alternative query examples and frames query as a visual/emotion search, but it does not clarify what draft refers to or how it connects to the video understanding map.

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?

Description states a specific verb-resource pair: 'Search and retrieve timestamped scenes from the video understanding map' and gives concrete query examples. This clearly distinguishes it from siblings like capcut_analyze_video_understanding or capcut_semantic_edit, which build or edit understanding rather than retrieve matching scenes.

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 phrase 'from the video understanding map' implies the tool is meant for querying an already-built map, and the examples clarify the visual/emotion query format. However, it never explicitly says when to use this tool versus capcut_analyze_video_understanding, capcut_semantic_edit, or other scene-related siblings, nor does it state the prerequisite that the map must already exist.

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