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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=false. The description adds genuinely new context beyond these: the operation is a queued (async) and priced (credit-consuming) job, and it returns video_id and video_uuid. It does not detail failure/retry behavior, but the added async+cost signals are the key traits an agent needs.

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 bracketed [write, queued, priced] tag is front-loaded and scannable, and the rest packs the required-param and structure hints without padding. The telegraphic, symbol-heavy style ("ugc_voice?", "sfx?") slightly reduces readability but wastes no words.

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 7-param, nested-object tool with no output schema, the description covers the most complex required parameter and the return keys. However, four optional parameters remain undefined in both schema and description, leaving the agent under-informed for anything beyond the mandatory path.

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 coverage is 0% and the objects are untyped (additionalProperties: true), so the description carries the burden. It helpfully explains video_ugc's shape (shop/brand, concept, scenes max 10, ugc_voice/ugc_motion/sfx) and that video_render_target is required, but leaves video_title, video_output, video_keywords, video_language and video_description undocumented.

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 promotion video of a shop from scenes") and distinguishes itself via the no-character mechanic where scenes are drawn by the image account and animated by the motion account. It doesn't name specific siblings like create_ugc_video or create_film_video, so routing relies on the agent inferring the scene-based distinction.

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 "no character" note and the REQUIRED flag on video_render_target imply constraints, and the max-10-scenes limit is a usable precondition. But there is no explicit "use this instead of create_ugc_video when..." routing despite many adjacent video-creation siblings.

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