video_transcript

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

With no annotations provided, the description bears the full burden. It discloses that it does not download videos for URLs and only extracts embedded subtitles for local files, clarifying it is non-destructive and does not perform speech-to-text. However, it does not state what happens when no subtitles exist or how language fallback works, nor mention any rate limits or side effects. These gaps are minor given the output schema exists, but the description could be more explicit about failure modes.

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 efficiently structured: a one-sentence purpose, a two-clause behavioral distinction, then a clean Arg list. It front-loads the most important information (what it does and how it differs by source type) before parameter details. Every sentence earns its place, with no fluff or repetition.

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 tool with an output schema, the description covers the essential context: purpose, source distinction, parameter semantics, and non-destructive behavior. It does not explicitly cover edge cases like missing subtitles or language fallback, but these are partially implicit. Given the complexity (4 parameters, two modes) and that annotations are absent, it is slightly thin on operational details but still sufficient for correct invocation in most 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 fully explain parameters. It does: the Args block describes each of the four parameters with examples ('en', 'de', 'ja'), clarifies that max_chars caps output with a default of 20000, and explains that timestamps are prefixed as [MM:SS]. This adds meaning well beyond the schema's titles and defaults, giving the agent precise context.

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 ('Get a clean text transcript of a video') and immediately distinguishes two source types (URL vs local file) and the mechanisms used (yt-dlp for captions, embedded track extraction). This clearly differentiates it from siblings like video_info, video_frames, and audio_transcribe, which serve different purposes.

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 explains the two modes of operation (URL vs local file) and notes that it does not download videos, which sets expectations. It does not explicitly list alternatives or exclusion conditions (e.g., when to use audio_transcribe instead), but the differentiation is implicit through the mention of captions/subtitles rather than audio transcription. This provides clear usage context without explicit 'when not to use' guidance.

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