extract_audio

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

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral trait – that the operation is a stream copy (fast, no quality loss, but fails or produces nothing if the container has no compatible audio stream) – yet it says nothing about what happens to an existing output file, whether the overwrite flag silently replaces data, or what errors look like.

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 front-loaded sentence with the method qualifier in parentheses; nothing is wasted and the key constraint appears immediately.

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, but a file-mutating tool with zero annotations and zero parameter documentation leaves the agent guessing about overwrite semantics, path handling, and failure modes. The description is too thin for that burden.

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%, so all three parameters (input, output, overwrite) are undocumented in structured data. The description mentions no parameters at all – not the path formats, not the meaning of overwrite, not whether directories are created – so it fully fails to compensate for the coverage gap.

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 states a specific verb (extract) and resource (audio track from a video) and specifies the method (lossless stream copy). It partially distinguishes itself from siblings like transcode_audio and remux_video by declaring losslessness, but never names them, so the differentiation is implicit rather than explicit.

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 'losslessly (stream copy)' implies the usage condition: use this when you want the audio without re-encoding. However, there is no explicit statement of when to prefer this over transcode_audio or extract_stream, and no mention of preconditions such as the input actually containing an audio track.

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