likenessforge_prepare_training

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

Beyond the annotations, the description discloses that the call is asynchronous and returns a retained background job, and it enumerates the effect categories (write, inference, download, network) while pointing at danceflow_component for conditional effects and noting on-demand model weight downloads. This is meaningful disclosure for a non-idempotent, open-world operation. It stops short of saying what files land in the output path or whether an interrupted job leaves partial artifacts.

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?

Three short sentences with the capability and its scope stated first, followed by the async contract and effect metadata. The effect-flag sentence is compressed to the point of being cryptic, but nothing is wasted or repeated.

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 output schema removes the need to describe return values, and the polling pointer covers the async lifecycle. However, for a tool with ten nested inputs and a permissions gate, an agent is left without any guidance on the format of images, output, or trigger, or on which permission flags must be acknowledged for this specific operation.

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 description adds no meaning for any of the roughly ten nested arguments — face, images, output, trigger, background, detector, segmenter, and trainer all go unexplained, and the permissions object's flags are only gestured at via "Base effect flags". With the schema's prose coverage at 50% and concentrated on a single boolean, the description does not compensate for the gap.

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 names a specific verb and resource ("Prepare authorized segmented face crops") and draws an explicit boundary against a sibling operation by stating it does so "without training a LoRA", which separates it from likenessforge_train_lora. It does not clarify how it relates to the closely named likenessforge_faces, which likely produces the input crops.

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?

Usage context is only implied: the phrase "without training a LoRA" signals this is a preprocessing step, but the description never states when to choose it over likenessforge_train_lora, likenessforge_faces, or likenessforge_train_wizard. It does supply a concrete follow-up instruction (poll danceflow_job_status), which is genuine workflow guidance.

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