transcribe_video

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the fallback behavior of 'auto', the local transcription behavior of 'whisper', and the audio retention/deletion side effect of keep_audio. Yet it omits other behavioral traits such as prerequisites (network/supported platforms), failure modes, or side effects of parameters like prefer_auto or want_vtt. Adequate but incomplete.

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 compact and well-structured: a one-liner stating the core purpose, followed by method breakdown and the keep_audio side-effect note. Every sentence earns its place; there is no redundant or filler content. The 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 the tool has 8 parameters and an output schema exists, the description need not explain return values. However, it leaves several parameters (language, want_vtt, prefer_auto, return_segments) unexplained, and it does not mention prerequisites like checking supported_platforms. The description is sufficient for basic usage but not fully complete for an agent to call the tool confidently in all scenarios.

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 0%, so the description must compensate. It does explain method, quality, and keep_audio with useful detail. However, it leaves url, language, want_vtt, prefer_auto, and return_segments entirely unexplained. The description adds value for a subset of parameters but fails to cover the majority.

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 crisp, specific verb-resource statement: 'One-call video → transcript.' It then distinguishes the three transcription modes (auto, captions, whisper), making it clear this tool performs full transcription and is distinct from siblings like video_info, fetch_transcript, or download_audio.

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 offers clear guidance for choosing among the 'method' values (auto vs captions vs whisper) and explains the keep_audio behavior. However, it never references sibling tools or gives explicit when-to-use vs when-not-to-use guidance (e.g., 'use fetch_transcript if you only need existing captions'). The usage advice is implied, not explicit.

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