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

Despite annotations providing no hints (all false), the description discloses a critical behavioral requirement: the tool returns identifiers that must be passed to `creations_show` for results to render. It also warns about image reference format ('never `webUrl`') and directs to `video_models_list` for limits. These go beyond the annotations, though it doesn't explicitly state side-effects like credit consumption or creation of a persistent resource.

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 every sentence/class performs a distinct job: primary action, prerequisite workflow, model selection, image ref rules, limits, and post-processing. It's not as terse as a two-sentence example, but it stays on-point and avoids fluff, with a logical flow from preparation to follow-through.

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?

Given there's no output schema, the description needs to convey what the tool returns and what to do next. It does this by referencing 'returned identifiers' and mandating `creations_show`, making the tool's contract clear. It also hint at constraints via 'Limits: `video_models_list`'. While it doesn't enumerate every possible restriction (e.g., rate limits, file size caps), it provides enough actionable context for an agent to use the tool successfully.

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 by explaining how to pick a model (`slug` from `video_models_list`), when to omit it (auto-select), and how to pass image refs ('use an asset URL or a creation `identifier`; never `webUrl`'). This directly clarifies the `slug` and `references` parameters within the nested `video` object, though it doesn't address `folderReference` or other fields.

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 description clearly opens with 'Generate video.' and immediately distinguishes this tool from siblings by referencing `video_plan` for the expected pre-work and `video_models_list` for model choice and limits. It specifies the exact action (generate) and the resource (video), and differentiates itself from related tools like `magnific_video_concatenate` and `magnific_video_speak`.

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 explicit when-to-use and when-not-to-use instructions: 'External clients: call `video_plan` first... skip only if the user explicitly says "just generate" or "one-shot".' It also mandates a follow-up call ('you MUST call `creations_show` once') and names the alternative (`video_plan`) and source for limits (`video_models_list`).

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