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

Annotations only state the generic flags (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description goes further by disclosing the concrete side effects (a new draft is saved, the review widget is rendered), that repeated calls create separate drafts, that nothing is generated and no credits are spent, and that no sign-in is required. That is exactly the extra context an agent needs before calling a non-idempotent prepare step.

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 purpose, then behavior, then usage boundaries. Every sentence carries load: the credit/sign-in assurances and the exclusion list all change agent behavior, and the draft-duplication warning is placed immediately next to the side-effect sentence.

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?

With an output schema present, return values need no prose, and the description covers cost, auth, idempotency and eligibility. It stops short of explaining how this hands off to `render_media_widget` or `update_media_project`, and leaves `model_name` unexplained, which is a modest gap for a 6-parameter tool.

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 50%, and the description only gestures at the documented half (model, aspect ratio, video duration, text prompt). It adds nothing about the `tab` selector beyond 'image or video', and says nothing that disambiguates `model_id` from the undocumented `model_name`.

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 ('Prepare an Abracadabrax image or video generation from a text prompt') and immediately scopes the artifact it produces: a draft plus a review widget. The image/video split matches the enum on `tab`, so an agent knows exactly what class of operation this is.

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 an explicit when ('only for text-to-image or text-to-video prompts') and a long, specific when-not list (uploaded/attached/reference images, editing, background removal, upscaling, try-on, image-to-video, media-to-media). It routes by workflow rather than by naming the alternative tool, so the agent still has to infer whether `generate_media` is the counterpart.

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