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

Beyond the annotations, the description adds meaningful behavioral context: edits are pinned to the farm account, only own videos can be edited, each edit costs 20 credits, the model choice is constrained, and the operation affects the whole clip. This goes well beyond the structured annotation hints and helps an agent predict side effects.

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 front-loaded with the core purpose and examples, then adds constraints and exclusions. Nearly every sentence contributes, though the farm-account and credit details are somewhat redundant and could be tightened without losing meaning.

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 mutation tool with no output schema, the description covers the operation, constraints, and costing well, but it omits what the response looks like, whether the edit is asynchronous/job-based, and the meaning of include_preview and aspect. It is adequate for basic invocation but not fully complete for an agent working without prior service knowledge.

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%, so the description must carry parameter meaning. It usefully documents media_id (must come from a previous generate_video* result) and gives examples for prompt, but aspect and include_preview are never explained. It also says 'abra_edit is the only model Flow offers here' while the schema enum includes abra_edit_360p, which is confusing for video_model_key.

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?

The opening sentence, 'Rewrite a video this service already generated, from a plain description,' clearly states the verb, resource, and operation. It includes concrete examples and explicitly distinguishes itself from a mask/region editor, so an agent can tell it apart from generate/motion/upscale 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?

It gives clear when-to-use context: editing only our own previously generated videos with whole-clip changes made through natural-language prompts. It also gives a strong exclusion: 'It is not a mask tool: describe the change, not the region.' It does not explicitly name sibling alternatives like extend_video or generate_video_from_image, but the boundary is clear.

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