transcribe.audio

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

No annotations provided, so description fully carries behavioral disclosure. It discloses that long recordings are split, language is auto-detected when not provided, and details return values including punctuated transcript, confidence, duration, language, timestamps, and speaker utterances when diarize=true.

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?

Two sentences, front-loaded with purpose and constraints in parentheses, then lists return values. Every sentence adds essential information without 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 audio transcription tool with no output schema, the description comprehensively covers inputs (formats, size/duration, optional parameters), behavior (language auto-detection, splitting long recordings), and outputs (transcript, confidence, duration, language, timestamps, utterances). No gaps.

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% with descriptions for url, diarize, language. Description adds context: url must be public, diarize enables speaker labels, language is a BCP-47 hint. Adds value beyond 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?

Description clearly states it transcribes audio to text with specific verb 'Transcribe an audio file URL to text', lists supported formats, size/duration limits, and distinguishes from sibling tools like ai.summarize which are not transcription-specific.

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 explicit constraints: formats, ≤15 MB, ≤15 minutes, and suggestion to split longer recordings. Lacks explicit when-not-to-use or comparison to alternatives, but usage context is clear.

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