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

Annotations already flag destructiveHint=true and non-idempotent, and the description usefully adds that the call is queued/async ('queued'), that it is a paid operation ('priced'), and that a render step must follow. It does not say what happens on failure or how long the queued job runs, keeping it from 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?

Front-loaded with the action and bracketed trait tags, then the object shapes and the required-field callout. The telegraphic style packs a lot in, though the shape literals make it read more like a schema digest than prose.

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?

Since there is no output schema, naming the returned video_id/video_uuid is valuable, and the render_video follow-up closes the loop. Yet for a 7-parameter nested-object mutation, leaving the title/keywords/language/description/output parameters unexplained is a real gap for an agent composing the call.

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 0% schema description coverage and nested objects, the description carries the load and does define video_ugc sub-fields (character_uuid, advertisement, ugc_prompt, ugc_duration 5-45s, ugc_voice, sfx, scene_ai) and the required video_render_target shape. However, five of the seven top-level parameters (video_title, video_output, video_keywords, video_language, video_description) get no mention at all.

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 and resource ('Create a UGC product video') and immediately defines the artifact: a READY character presenting an advertisement, with worker_videos_ugc assembling script, voice, clips and timeline. This clearly separates it from the generic create_video, create_promo_video and create_film_video siblings.

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?

Gives a clear workflow context (call this first, then render_video once the timeline is built) and states the READY character prerequisite plus the mandatory render target. What it lacks is an explicit 'use X instead when...' comparison against the other three video-creation siblings.

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