likenessforge_train_wizard

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

With readOnlyHint=false, openWorldHint=true and idempotentHint=false already declared, the description adds real value: it discloses that the call returns a retained background job (rather than blocking) and enumerates the effect flags (write, inference, download, network, training) the agent must acknowledge. It does not say whether repeated invocations create duplicate jobs or what gets written to disk, which keeps it short of a 5.

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, front-loaded with the action and immediately followed by the async contract and effect disclosure; nothing is padding. It is somewhat jargon-dense ('bounded candidate LoRAs', 'fixed holdout repairs') without unpacking the terms.

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?

Because an output schema exists, return values needn't be described, and the async job + polling story is covered. Still missing for a multi-effect, non-idempotent training operation: the prerequisite relationship to likenessforge_prepare_training, the distinction from likenessforge_train_lora, and where artifacts land.

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 most of the ~17 nested arguments (images, output, trigger, validation, preset, face, seed, trainer, detector, low_vram, segmenter, modifier, prompt) carry no description at all. The description explains none of these — notably the quick/balanced/thorough preset and the 'fixed holdout' validation input — so it fails to compensate for the coverage 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: training bounded candidate LoRAs plus a fixed holdout comparison. That is clearly distinguishable from generic siblings such as danceflow_search, but it never states how this 'wizard' differs from likenessforge_train_lora or likenessforge_prepare_training, so sibling differentiation is only partial.

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?

It gives one concrete follow-up instruction ('poll danceflow_job_status') and one routing hint ('Inspect danceflow_component for conditional inference/download effects'), which is genuine usage guidance for the async flow. However, there is no statement of when to choose this over likenessforge_train_lora or the prepare/repair wizard siblings, nor any prerequisites such as needing a prepared dataset.

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