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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description still adds real context beyond them: billing is driven by duration and resolution, and an uncertain result should be retried with the same inputs plus the same idempotency key. It omits whether the call is asynchronous and what the returned task looks like.

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?

Three tight sentences, each earning its place: purpose, geometry rule, then billing and retry semantics. Front-loaded with the core action and no filler.

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-parameter, no-output-schema submission tool, the description covers the essentials of geometry, cost, and idempotent retry but omits the mode enum, audio removal, naming, and what the call returns. Enough to submit a basic job correctly, not enough to use the full surface confidently.

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% across 14 parameters, so the description must carry the burden and largely does not. It clarifies the x1/y1/x2/y2 rectangle convention and the idempotency key's retry role, but leaves mode (normal vs protect), removeAudio, coverUrl, fileName, width/height/duration, and the videoUrl-vs-mediaId choice completely unexplained.

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 ('Submit a video to erase hardcoded subtitles or visual watermarks'), which is far more informative than the bare tool name. It does not, however, distinguish itself from close siblings like remove_video_watermark or submit_media_task, so an agent is left to infer which submission path applies.

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 conditional guidance for the rectangle case ('full-frame by default; provide all x1, y1, x2, y2 only for a user-supplied rectangle') and retry guidance, which is genuinely useful. But it names no alternative tools and never says when to prefer this over remove_video_watermark or submit_media_task, so the when-to-use decision against siblings is left implicit.

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