media_youtubeDownload

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

Goes well beyond the annotations (openWorldHint=true, destructiveHint=false) by disclosing the default transcode behavior (mp4 H.264+AAC, VP9/AV1 transcoded via ffmpeg for AE/Premiere), the default filename template, and a licensing caveat. It omits auth/rate-limit behavior and what cookiesFromBrowser implies, which keeps it below a 5.

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?

A single front-loaded block that opens with the core action before enumerating formats and extras; nearly every clause conveys a distinct capability. It is dense but not padded, though a bulleted structure would scan faster for 14 parameters.

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 14-param, nested-object, no-output-schema tool, the description covers the decisions that matter (format, quality, clipping, playlist, Adobe import). The gaps — output directory behavior, maxItems on playlists, cookie/auth usage — are the remaining pieces an agent would still have to infer.

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?

With only 29% schema coverage across 14 params, the description carries real weight: it enumerates the full quality ladder (best|2160|...|360) that the schema leaves as a bare string, lists formats matching the enum, explains start/end clipping, subtitles, thumbnail, playlist, and Adobe import. It leaves outputDir, maxItems, cookiesFromBrowser, and filename semantics largely to the 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?

States a specific verb+resource ('Download video or audio from YouTube') and even expands scope ('videos, Shorts, playlists — and 1000+ other sites') with the underlying engine named (yt-dlp). An agent can immediately distinguish this from sibling media tools like media_info, media_import, or pixabay_download.

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?

Clear context for when this applies: pulling web video/audio, optionally editing clips, optionally importing straight into an Adobe app. It does not name an alternative or exclusion (e.g., when to prefer pixabay_download for stock, or media_info for inspection), so it stops short of full when/when-not routing.

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