generate_capcut_draft

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

With no annotations at all, the description carries the full burden. It does disclose useful behavior: real JSON files are written to disk, output_dir defaults to CapCut's native drafts directory, and defaults for width/height/fps/ratio are given. It omits what most matters for a filesystem-writing tool — whether an existing project of the same name is overwritten, whether the directory is created, and how missing or invalid clip paths 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?

Front-loaded with the verb and output artifacts, then structured as a conventional Args block that maps one-to-one onto the schema parameters. The Returns section partly duplicates the output schema, but overall there is little wasted prose.

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?

Eight parameters, no annotations, and a nested untyped clips array make this a moderately complex tool, and the description covers the parameter shapes well. It falls short on operational behavior — overwrite semantics, failure modes for bad paths, and disk-location constraints — which an agent needs before generating files into a user's CapCut drafts folder. The existence of an output schema means the return description needn't be exhaustive.

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 0% and the clips/audio_tracks items are bare objects with additionalProperties, so the description is doing real work by naming the expected keys ('path', 'start_sec', 'end_sec', 'speed', 'volume'; 'path', 'timeline_start_sec', 'volume') and the accepted ratio values. Remaining gaps are minor: no units or accepted ranges for start_sec/end_sec, volume, or speed, and no constraint linking width/height to ratio.

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?

Names a concrete verb (Generate) and concrete artifacts (draft_content.json and draft_meta_info.json project files) plus the target applications. The sibling tools (remove_silence, smart_crop_vertical, apply_lut_grade, extract_audio_and_metadata) are all single-purpose media operations, so the distinction is obvious without needing an explicit negative statement.

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 line about being 'directly importable into CapCut Desktop / Jianying Pro without manual timeline setup' implies the context of assembling finished clips into a project, but there is no explicit when-to-use instruction, no mention that it should be run after the sibling processing tools, and no stated preconditions such as clips already existing on disk.

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