voice_to_draft

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

With no annotations provided, the description fully carries the burden. It discloses the transcription model (Whisper), the cleaning of filler words, the output as a draft, and the required dependencies. No contradictions.

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, no wasted words. Front-loaded with the core action and key constraints. Excellent conciseness.

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 the 3 parameters, low schema coverage, no output schema, and no annotations, the description is fairly complete. It covers input format, dependencies, behavior (clean, draft), and output intention. Could mention error handling or size limits, but overall sufficient.

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 33% (only audio_path described). The tool description adds supported file formats and the nature of audio_path as an absolute path. Language default and tone enum are listed but no further guidance on choosing tone values. Provides some extra context but not comprehensive.

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 states the tool transcribes audio files and produces an AI-drafted LinkedIn post, specifying supported formats and explicitly noting that it does not post automatically. This distinguishes it from sibling tools like create_post.

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 clear context: it returns a draft for human review and does not post automatically, implying when to use versus posting tools. It mentions system requirements (ffmpeg, faster-whisper) but does not explicitly list when not to use or alternatives.

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