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

With no annotations, the description carries the full burden and does well: it discloses that the operation is asynchronous (poll with wait_for_video), that input must be a direct file URL rather than a page URL, that cost scales with model and duration, and that some hosts render a live preview. It omits failure behavior, typical completion time, and whether credits are consumed on failure.

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 purpose, then the credit/model table, then the operational steps, ending with the preview note. Every sentence earns its place, though the compressed credit notation ('6 / 11 / 16 credits for up to 5s / 10s / longer') takes a moment to decode.

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?

No annotations and no output schema, so the description must cover the workflow — and it does, naming the polling companion tool and the cost model. The main residual gap is that it never states what the tool returns (e.g. an outputUrl) or how long the job typically takes, which an agent must know to hand off to wait_for_video.

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 100%, so the baseline is 3, but the description adds real meaning: videoUrl must be a direct video file URL with concrete .mp4 / outputUrl / upload_file examples, and the model enum is annotated with credit pricing at different durations. That is substantive semantics beyond the schema's 'Direct URL of the video file to upscale.'

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 — 'Upscale a video's resolution and sharpness' — with the parenthetical '(Video Upscaler)' clarifying the feature identity. It is trivially distinguishable from upscale_image by resource type and from create_video by being an enhancement rather than a generation.

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 concrete operating guidance: pass a direct video file URL (explicitly a generation outputUrl or upload_file url) and poll with wait_for_video. The per-model credit tables implicitly guide model selection by cost. It does not state exclusions — e.g. max input duration/resolution or when upscaling is inappropriate — so it stops short of a 5.

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