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

With no annotations, the description carries the full burden and does well: it flags that video is 'expensive' (cost profile), that generation is asynchronous and must be polled with wait_for_video, and that a live preview renders in app-capable hosts. It does not cover failure/refund behavior or auth requirements, so it falls just short of complete.

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?

Four sentences, front-loaded with purpose and use cases, then workflow, with zero filler. The inline model enumeration is long but plausibly useful for model selection; it is the only element that mildly dilutes density.

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-gated generation tool with no output schema and no annotations, the description covers cost gating, polling, model discovery and preview behavior. Minor gaps remain around idempotencyKey usage and what happens if a render fails or is rejected on credits.

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 coverage is 83%, so the schema already documents mode, model, inputs and maxCredits, giving a baseline of 3. The description adds real meaning by tying maxCredits to the get_price workflow ('pass them as maxCredits') and by directing the agent to list_models for valid mode/model/input keys, which the schema only references abstractly.

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 ('Generate a short video') plus the concrete use cases (social post, Reel, TikTok, ad), and enumerates the supported models. Combined with the sibling list (create_image, create_avatar_video, create_motion_control), an agent can immediately distinguish this from the other creation tools.

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 prerequisite chain: see list_models for modes/inputs, call get_price first, tell the user the credits, pass them as maxCredits, then poll with wait_for_video. It names three alternative sibling tools and the exact condition under which each is needed, leaving nothing to inference.

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