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

With no annotations, the description carries the whole burden and does so well: cost per minute of output, async job_id with a named polling tool, and a 1-hour link expiry. It omits auth requirements and error behavior, so it falls short of a 5.

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?

Four short sentences, each carrying a distinct fact (purpose, track selection, cost, async/expiry), with the primary purpose front-loaded. Nothing is redundant.

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?

No output schema exists, but the description explains the return path (job_id, poll via get_job, expiring links) and the cost model, which is exactly what an agent needs to plan a call to this tool.

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 100%, so the schema already documents all six parameters with enums, bounds, and defaults; baseline is 3. The description only adds the notion that audio_track matters when a file has several tracks, which is marginal beyond the schema.

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+resource ('pull the audio track out of a video') and expands scope to a second case ('or re-encode an audio file'). This clearly distinguishes it from nearby siblings like process_audio, trim_media, and compress_media.

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?

Gives useful context — choose the track when multiple exist, and poll with get_job for long jobs — but never states when to prefer this over alternatives such as process_audio or trim_media. Usage is implied rather than routed.

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