list_modelsList the available AI models with their kind (image, video), default cost in credits (1 credit = $0.012, or €0.01 when billed in euros) and billable options. Call this before generating if you need a specific model, otherwise sensible defaults are used.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Only return models of this kind. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It communicates a read-only listing operation and reveals the meaningful output contents. It omits pagination/auth details, but those are not critical for a simple discovery 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?
Two concise sentences with no filler. The core purpose is front-loaded, and the usage guidance is packed efficiently into the second 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?
The tool is simple with one optional parameter and no output schema. The description covers purpose, output contents, and when to use it. It could mention the exact response shape, but this is not essential for an agent to invoke the tool correctly.
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?
The input schema already documents the optional 'kind' parameter with an enum and description, and the schema coverage is 100%. The description adds no additional parameter-level meaning beyond restating the kind categories.
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 uses a specific verb 'List' with a clear resource ('available AI models') and names the key attributes returned (kind, default cost, billable options). It is clearly distinguishable from the sibling generation and status 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?
The description explicitly states when to call this tool: before generating if a specific model is needed, and notes that otherwise sensible defaults are used. It does not name the sibling tools directly, but 'generating' clearly implies generate_image/generate_video as the alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct purpose: image generation, video generation, status polling, and model listing. There is no functional overlap between them; the async nature of video generation and the status tool clearly complement each other without ambiguity.
All tool names follow a consistent verb_noun snake_case pattern: generate_image, generate_video, get_generation_status, list_models. The verb prefixes (generate, get, list) map predictably to actions and resources.
With 4 tools, the set is tightly scoped for a media generation server. Each tool serves a necessary role: creating images, creating videos, checking async status, and discovering models. No redundant tools exist.
The domain is AI media generation, and the lifecycle is fully covered: start an image generation, start a video generation, poll for status/results, and list available models. There are no dead ends; even timeout scenarios are addressed via get_generation_status.