Transcribe audio

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

Goes well beyond annotations by revealing that transcription can take roughly real-time on CPU, that the first run downloads model weights, that language auto-detection occurs unless specified, and that output includes timed segments with optional word timings. This is rich behavioral detail not present in the annotations.

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 tightly written across three short paragraphs, each sentence adding valuable information: purpose, output format, performance characteristics, and model weight download. No fluff or redundancy.

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?

For a complex asynchronous transcription tool, the description covers return format, optional parameters, runtime expectations, polling behavior, and initial setup (model weights). It is sufficiently complete given the presence of an output schema.

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 high (67%), but the description adds meaningful semantics: it explains the effect of language auto-detection, mentions srt_path writing a subtitle file, and clarifies word_timestamps usage. This complements the schema rather than just repeating it.

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 opens with a specific verb+resource: 'Transcribe speech in an audio or video file using Whisper.' This clearly states what the tool does and distinguishes it from siblings like auto_caption or translate_transcript by naming the tool and the core function.

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?

Provides clear operational context: mentions polling job_status because transcription is slow, describes model choices, and explains when word_timestamps and srt_path are useful. However, it does not explicitly exclude alternatives or name sibling tools for comparison, so it falls just short of full guidance.

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