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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the description needs to add context such as whether this creates an async job, what the returned artifact is, or how source_id chaining behaves. It adds none of that — the format list merely restates the schema enum.

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?

One front-loaded sentence with no padding. The trailing format list is somewhat redundant with the schema enum but is not wasteful enough to penalize heavily.

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 no output schema, the description should reveal what the caller gets back and whether the call is async or job-based; it says only that an audio file results. The mutually exclusive source_id/video_url pattern is covered by the schema, so that gap is mitigated.

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 100%, so the schema already explains format, source_id, and video_url in detail. The parenthetical format list duplicates the enum without adding syntax or priority information, so baseline 3 applies.

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?

States a specific verb and resource ('Extracts the soundtrack of a video as an audio file'), which an agent can distinguish from audio-mutating siblings like clean_audio. It does not explicitly contrast with any sibling, but the operation is unambiguous.

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 gives no when-to-use guidance, no prerequisites, and names no alternative (e.g., clean_audio for already-extracted audio, transcribe_video for text output). Selection is left entirely to inference from the name.

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