Detailer Pass

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

With no annotations, the description must explain side effects, return values, and runtime behavior. It only states it is 'a standalone operation' and mentions the fallback logic. It does not say whether the operation mutates stored state, its compute cost, what happens on detection failure, or the response format. Since no output schema exists, this lack of behavioral detail is a serious gap.

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 brief (one sentence plus a fallback note) and correctly names the endpoint. However, for a 31-parameter standalone API call, it is severely under-specified; the front-loaded 'standalone' concept is good, but critical context like model selection, expected input format, and result handling is absent. Conciseness is good, but at the cost of completeness.

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?

With no annotations, no output schema, and only 6% schema coverage, the description bears the full burden. It fails to explain return values, error cases (e.g., no detections), or the interplay between detailer_* flags Mkargs. The fallback note is helpful but insufficient for a 31-parameter complex tool. The context about 'standalone vs. base pass' is the only contextual anchor.

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 coverage is only 6%, with 31 parameters. The description adds no per-parameter meaning beyond the fallback note. It does not define what 'detailer_*' parameters control, how segmentation/thresholding work, or what the resolution/strength values do. The fallback sentence is the only parametric insight and it's vague about the source of global defaults.

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 verb 'run' and resource 'YOLO detailer' are clear, and 'standalone operation' with 'no base generation pass' distinguishes it from a combined txt2img+detailer flow. It does not explicitly name sibling tools like sdnext_txt2img or sdnext_extra_network_detail to differentiate, but the edge case is understandable. Score 4.

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 implies use for detail-only processing of an existing image ('standalone operation'), but does not explicitly state when to choose this over sdnext_img2img or how parameter fallback affects selection. It also does not mention the companion sdnext_list_detailers tool for model discovery, despite its clear relevance. The phrase 'fields fall back to global settings' is useful but under-specified. No explicit 'use when' guidance—only a negative constraint.

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