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

The description discloses important behavioral traits beyond the sparse annotations: credit costs, the need for a connected Photo AI Studio account, and the side effect of starting a sign-in flow. It does not explicitly mention the asynchronous prediction_id/polling behavior in the main text, but the wait_for_result parameter schema covers that. No contradiction with annotations.

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 compact and front-loaded: core purpose and cost appear first, followed by a clean bullet list of types. Every sentence contributes value, with no repetition of schema details. The structure is easy to scan and parse.

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 a 16-parameter tool with no output schema, the description provides a solid mental model: what the tool creates, which parameters belong to which type, and the auth/cost context. The return-and-polling behavior is only present in the wait_for_result parameter description rather than the main description, but that is acceptable because the full tool definition includes it. The description is complete enough for an agent to select the tool and construct a valid request.

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 100% schema description coverage, the baseline is 3, but the description adds a higher-level type-to-parameter mapping (image_to_video uses image_url/prompt; ugc uses script/voice_id; product_holder uses product_image_url). This helps an agent select the correct parameter set per type beyond what each property's schema description states. The cost implications tied to output_type are also useful.

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 and resource, 'Create an AI video,' and immediately enumerates three concrete generation types (image_to_video, ugc, product_holder). This clearly differentiates the tool from sibling tools like generate_photo and edit_image, which focus on static image tasks. The cost line also clarifies that product_holder can produce an image, adding useful scope nuance.

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 gives clear context for when to use this tool—creating AI videos or product_holder images—and maps each type to its key parameters. However, it never explicitly states when not to use it or points to alternatives, such as using generate_photo for normal photos. The account-requirement note is a helpful prerequisite but not a routing rule.

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