split_audio

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

No annotations are provided, so the description must disclose behavioral traits. It does mention the return structure ('Returns len(points)+1 ordered segments with paths and durations') and the 'strictly increasing' constraint on split_points_s. However, it omits side effects (e.g., whether the original file is modified), permissions, or error behavior. The output schema covers return values, so the description's mention of them is somewhat redundant, leaving the behavioral disclosure incomplete.

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 four sentences, each adding distinct value: the core action, return behavior, a concrete workflow, and a constraint. It front-loads the verb and resource, and the structure is logical, though the workflow sentence is somewhat dense. No significant redundancy exists, making it efficient without being terse.

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?

The presence of an output schema reduces the need to document return values. The workflow context is strong and gives the agent a clear use case, but the description does not address failure modes, prerequisites (e.g., file existence, MP3 format), or the behavior of output_dir. Given no annotations and 0% parameter coverage, the description leaves operational gaps that could hinder correct invocation in edge cases.

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?

With schema description coverage at 0%, the description must compensate for all three parameters. It explains split_points_s (units and constraint) and implies audio_path is the mp3, but output_dir is never mentioned or explained. The description also does not clarify the expected format of audio_path (e.g., path vs. URI). This leaves a meaningful gap for one of the parameters, so the description only partially compensates for the missing schema documentation.

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 uses a specific verb ('Cut') and resource ('master voiceover mp3'), and further clarifies the operation by referencing split points. It clearly distinguishes itself from sibling tools like trim_video and retime_video by focusing on audio segmentation. The function is unambiguous and immediately understandable.

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 explicitly outlines a full workflow: generate a master VO with generate_elevenlabs_voiceover, pick sentence-boundary timestamps, split here, then pass each segment to generate_seedance_video. This tells the agent exactly when to use this tool and how it fits into a larger pipeline, while also implicitly differentiating it from other audio/video editing siblings.

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