Text to Image

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns base64 images, an info string, and echoed parameters, plus mentions that save_dir creates a local directory and send_images controls response behavior. However, it does not disclose computational cost (GPU/time), caching behavior, rate limits, or potential side effects like writing to disk (unless save_images/save_dir set). For a complex generation tool, this is moderate coverage.

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 a single comprehensive sentence, front-loaded with 'Generate images from text prompts'. It crams many feature names but each is a recognizable keyword. It's a bit noun-heavy but acceptable for a feature-rich tool. No fluff, but the list of features is a bit dense.

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?

Given 65 parameters fully described in schema and no output schema, the description covers the core purpose and return format. However, it doesn't mention execution time, memory requirements, or that the tool may be slow/expensive, which is relevant for an agent deciding whether to invoke. Slightly above average because the feature list guides what to set, but gaps around operational context.

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 100%, so each of 65 parameters has a description. The tool description adds value by mentioning that some parameters are sourced from list tools (e.g., sampler_name from sdnext_list_samplers, models from sdnext_list_controlnets), which is also in schema but the tool description reinforces. However, it doesn't add parameter-relationship or workflow hints beyond schema. With full schema coverage, a 3 baseline, but the description's mention of LoRA syntax and endpoint provides some added semantics.

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 clearly states the tool generates images from text prompts, references the underlying SD.Next API endpoint (/sdapi/v1/txt2img), and enumerates supported features (samplers, guidance, hires fix, refiner, detailer, LoRA, styles, scripts, control units, face modules, XYZ grid). This distinctly separates it from sibling tools like sdnext_img2img (image-to-image) and sdnext_control. The verb 'generate' and resource 'images from text prompts' are specific.

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 usage for text-to-image generation and hints at feature selection (e.g., mentioning LoRA syntax, styles, scripts), but does not explicitly state when to use this over sdnext_img2img or sdnext_process_image. It lacks explicit when-not or alternative guidance. The API endpoint mention is helpful context, but no exclusion criteria are given. Without sibling differentiation, it's slightly above baseline because the feature list suggests richness.

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