likenessforge_repair_wizard

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

Annotations already declare non-read-only, non-destructive, open-world, non-idempotent. The description adds material context beyond that: the call returns a retained background job rather than results, and the base effect flags are write, inference, download, and network. It stops short of explaining what a 'bounded repair comparison' actually writes or what the manifest contains, but the async and effect disclosure is substantive.

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?

Four compact sentences with the purpose front-loaded and no filler. The effect-flag and component-routing sentences are terse but each carries operational meaning, though the flag list reads slightly like internal metadata dump.

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 presence of an output schema means return values need not be described, and the job lifecycle plus effect flags are covered. However, for a tool whose real complexity lives in an undocumented fourteen-field argument object, the description does not give the agent enough to populate a correct call beyond the required trio.

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 schema's nested argument object holds roughly fourteen properties (image, output, face, preset, lora, prompt, references, low_vram, etc.) with virtually no per-field descriptions; only allow_downloads and permissions carry text. The macro description mentions no parameter at all, so nothing narrows what 'image', 'output', 'face', or 'preset' mean for this specific operation.

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 gives a concrete verb-plus-resource: 'Create a bounded canonical repair comparison and evidence manifest.' That is a specific, distinguishable artifact rather than a restatement of the name. It never contrasts with the sibling likenessforge_repair, so an agent must infer which repair path applies.

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 a genuinely useful follow-up instruction ('poll danceflow_job_status') and routes the agent to danceflow_component for conditional effects, which is real when-to-do guidance. It does not state when to choose this wizard over likenessforge_repair or likenessforge_train_wizard, so the primary selection decision is left implicit.

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