ytdlp__download_video_subtitles

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 discloses some important behaviors: downloads both manual and auto-generated subtitles without the video, saves to output_dir with a fallback chain (YTDLP_OUTPUT_DIR, SHELL_AS_MCP_OUTPUT_DIR, ~/Downloads), and caps maxRetries at 2. However, it does not state whether existing files are overwritten, what happens when subtitles are unavailable, or what the return value looks like. This is a moderate level of transparency.

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 first sentence stating the purpose, a @remarks line with a key behavior, then a clean @param list. There is no filler or redundant content. Every sentence and parameter line adds useful information, and the format is easy to parse.

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?

The tool has 7 parameters, no output schema, and no annotations, so the description must cover essentials. It does cover the operation, output location fallback, and parameter semantics. However, it lacks a description of the return value (e.g., saved file paths) and does not mention failure modes or prerequisites like yt-dlp availability. These gaps prevent it from being fully complete, though it covers the core functionality.

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?

The input schema has 0% description coverage, but the description compensates with detailed @param annotations for all seven parameters. For example, it specifies URL must start with http:// or https://, language defaults to 'en', output_dir has a specific fallback order, cookies must be Netscape-format, and maxRetries is capped at 2. This adds meaning beyond the raw schema. Some params like 'proxy' are terse, but overall all params are explained.

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 and resource: 'Download subtitle files (VTT) for a video URL using yt-dlp, saving to output_dir or a configured default directory.' It clearly distinguishes itself from sibling tools like download_audio, download_video, and download_transcript by explicitly stating it downloads only subtitle files, not the video, and that both manual and auto-generated subtitles are included.

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 provides clear context for use: it downloads subtitles without the video, which is a key differentiator. However, it does not explicitly mention alternatives or exclusions, such as 'use download_transcript for text transcription' or 'do not use if you need the video file itself.' The @remarks statement gives implied usage context but stops short of explicit when-to-use vs. alternatives.

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