Transcribe audio/video

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

Annotations already indicate idempotency and non-read-only behavior. The description adds valuable context: 'Audio is never used to train models' and the async job model. It does not cover rate limits or cost, but the additional privacy statement compensates.

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 three well-structured sentences. Each sentence adds distinct value: purpose, input options, and privacy/async handling. No wasted words, and key information is front-loaded.

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?

Given 11 parameters and no output schema, the description covers core aspects: purpose, inputs, async return, and privacy. It lacks detail on parameter interactions (e.g., quality vs. diarize) but references get_transcription for results, which suffices for completeness.

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 91% schema coverage, the description still adds meaning beyond the schema by explaining input types (e.g., YouTube, podcast feeds) and the return format. It also clarifies the mutual exclusivity of url and file_ref.

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 clearly specifies the verb (transcribe), resource (audio/video), and output (speaker-labeled, timestamped transcript with SRT/VTT captions). It distinguishes from sibling tools by emphasizing 'hours-long' content and the specialized output format.

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 provides clear input options (file_ref or URL) and context (long-form media). It mentions the async return pattern and references get_transcription. However, it does not explicitly state when not to use this tool or compare with siblings like transcribe_podcast_feed.

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