text_to_video

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool returns a task id, status, and output URLs, but omits critical behavioral traits: whether the operation is synchronous or asynchronous (wait parameter suggests polling), potential for long execution, authentication requirements, rate limits, or failure modes. The agent is left with insufficient transparency for a task-creation tool.

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 a single sentence with no waste, and the action is front-loaded. It is concise, but for a tool with 22 parameters, the brevity borders on under-specification. It earns its place but does not leverage the available sentence to add value beyond the one-line purpose. Score 4 for appropriate conciseness without penalizing the lack of detail.

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 the high complexity (22 parameters), absence of output schema, and zero annotations, the description is severely inadequate. It only states the return type but does not explain parameter constraints, default behaviors, or edge cases. An agent cannot correctly invoke this tool without external knowledge, making the description functionally incomplete.

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 only 18%, meaning 82% of parameters lack any explanation. The description does not compensate for this: it fails to explain any parameter semantics, such as the meaning of wait, seed, aspect_ratio, or the many reference inputs. It only provides high-level context ('text to video') without mapping to specific parameters, leaving the agent to guess the purpose of most 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 identifies the action (Create a Seedance task), the resource (RunAPI), and the domain (text to video). It distinguishes itself from sibling tools (login, get_task, check_pricing) by stating a unique verb and resource. The purpose is specific and unambiguous.

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?

The description implies usage for text-to-video generation but provides no explicit guidance on when to use this tool versus alternatives. It does not mention exclusions or conditions, and the lack of a direct comparison to siblings leaves the agent to infer applicability. No misleading guidance, but also no helpful routing.

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