Rd Generate

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

With no annotations, the description carries the full burden and discloses substantial behavior: the pixel output formula, 8px latent grid normalization, quality→steps mapping, cfg_scale/adherence semantics, and the 'other args ignored' preset override behavior. It is dense but genuinely informative; some jargon ('leco', 'ELLA/CLIP') is opaque.

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?

Every sentence carries technical payload and the content is clustered by topic (formula, sampling, modifiers, rendering, display, preset). It is a dense single paragraph with no visual breaks and heavy jargon, so readability is sacrificed, but no sentence is filler.

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 37 parameters, zero annotations, zero schema descriptions, and no output schema, the description covers parameter behavior well but leaves the return contract unspecified (no output schema means the agent must infer what the tool returns; return_image is never explained) and omits backend prerequisites (rd_start_backend is a sibling). Significant, but the dense parameter coverage lifts it above minimal.

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 0%, so the description must compensate, and it does: it maps meaning onto quality, cfg_scale, adherence, use_ella, size_preset, swap, pixel_size, comp_*, light_*, pixelvae, rembg, post_process, tile_x/tile_y, save_grid, save_progress, preset and overrides. A few parameters (loras, return_image, prompt_tuning) remain unexplained, but the bulk of the 37-parameter surface gets 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?

Begins with a specific verb-resource pair ('Text to Image with the local Retro Diffusion pixel-art model'). The 'local' qualifier separates it from rd_api_txt2img, but it does not explicitly name sibling alternatives, leaving the boundary with rd_cn_txt2img and rd_img2img to inference.

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?

No guidance on when to use this tool versus the many generation siblings (rd_api_txt2img, rd_img2img, rd_cn_txt2img, rd_texture_gen). The word 'local' implies an offline preference, but there are no explicit when/when-not conditions or alternative names.

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