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

Goes well beyond the annotations (which only say it is a non-idempotent, non-destructive write): it discloses per-second billing, that credits are held on acceptance and refunded on failure/cancellation, that oversized sources fail the job and refund, and that this is an async job returning {id, status} requiring polling of getApiJob. It also gives the concrete cost rate (0.2 credits/second).

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-loads the core action and the input constraint before the edge cases and billing. It is however dense and partly redundant, repeating the video eligibility rules already in the schema and stating the cost twice ('Billed per second of video' and 'Credits: 0.2 credits per second').

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 an async, credit-consuming mutation with no output schema, the description supplies the missing pieces an agent needs: the eligibility rules, the async contract ({id, status} plus getApiJob polling), the shape of the result (new URL at 2x, same duration, plus duration in seconds), and the credit/refund behavior.

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 100%, so both the 'video' and 'request_id' semantics are already documented in structured fields, including the listGenerations lookup trick. The description largely restates these constraints (7-day window, 960px limit, request_id tagging) rather than adding syntax, format, or edge-case meaning beyond the schema, so the baseline of 3 applies.

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 plus the exact transformation: 'Upscale a previously generated video to twice its resolution (2x).' It also scopes the accepted input to videos produced by createVideo, createVideoFromReferences, or editVideo, which cleanly separates it from upscaleImage and the creation 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 concrete selection criteria: use the URL returned by the three generation tools, within 7 days, and only when both dimensions are under 960px. It also names the alternatives ('createVideo for image-to-video, editVideo to modify a generated video') and warns that arbitrary external videos are rejected.

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