likenessforge_train_lora

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

Annotations only tell the agent this is a non-idempotent, open-world writer. The description adds real behavioral context beyond that: the call returns a retained background job that must be polled, the base effect set (write, inference, download, network, training), and that inference/download effects can vary by component. It still omits failure behavior and whether an existing output is overwritten.

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 tight sentences, front-loaded with purpose, then return behavior, then effect flags. The effect-flag enumeration is compact, though 'Inspect danceflow_component for conditional inference/download effects' reads as jargon that requires already knowing the sibling.

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?

An output schema exists, so return values need no explanation, and the description correctly covers the async job lifecycle and the permission/effect model, which are the two things an agent could not learn from annotations alone. The gap is the many training hyperparameters, none of which are addressed despite the thin schema coverage.

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 50% and only the two authorization booleans plus the permissions object carry descriptions. The description adds nothing about rank, steps, learning_rate, trigger, images, output, face, trainer, segmenter, detector, low_vram, or background, which are the settings an agent actually has to choose. 'Bounded settings' does not substitute for explaining any of them.

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 ('Train one explicitly authorized identity LoRA') plus scope qualifiers ('bounded settings', 'explicitly authorized'). It implicitly contrasts with likenessforge_train_wizard through the 'explicitly authorized / bounded' framing, but never names that sibling, so an agent still has to infer which entry point to pick.

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 useful post-call routing ('poll danceflow_job_status') and a conditional-effects pointer ('inspect danceflow_component for conditional inference/download effects'). It does not say when to use this versus likenessforge_train_wizard or likenessforge_prepare_training, nor what prerequisites must be satisfied before training.

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