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

Annotations already cover mutation and non-idempotency; the description adds meaningful context beyond them: 20-credit cost, account/project pinning, whole-clip behavior, and free-form prompt style. It could be slightly clearer that abra_edit_360p also exists despite the 'only model' wording, but this is not an annotation contradiction.

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 description is dense but not bloated; examples, constraints, and cost are front-loaded and every clause carries information. The centered block of examples is slightly heavier than needed but still useful.

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 mutating tool with no output schema, it covers prerequisites, ownership, cost, prompt style, and scope. It does omit the return/job-checking behavior, but that is a modest gap given the detailed usage guidance and existing check_job sibling.

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, the description compensates for the most important parameters: media_id's provenance/ownership and prompt intent with concrete examples. It does not explicitly describe aspect or include_preview, though their names, defaults, and enums make them largely self-explanatory.

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?

Opens with a specific verb and resource ('Rewrite a video this service already generated') and immediately distinguishes this from generation tools by requiring a previous generate_video* result. The 'not a mask tool' line plus whole-clip scope removes ambiguity with any region-editing interpretation.

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 precondition: media_id must come from a previous generate_video* result and can only be one of the service's own videos. It also states a when-not case ('not a mask tool'), though it does not name a specific sibling tool as the alternative for new-video generation.

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