novelai_generate

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

Adds substantial behavior beyond the annotations: it may spend account credits, it checks live entitlement and Huishu pricing, it never retries automatically, paid/unknown prices are gated behind explicit approval, and it returns images plus a run ID. These are exactly the side-effect and safety facts an agent needs that readOnlyHint=false and destructiveHint=false do not convey.

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?

Front-loads the purpose and mode coverage, then layers behavioral constraints. Dense but every sentence carries operational information; it is slightly long, though nothing is clearly redundant.

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?

For a high-complexity generation tool with a large nested request schema and no output schema, the description covers the approval gating, cost risk, and return value well. It leaves the construction of the large official request payload to the schema, which is acceptable given the schema's detail.

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 already 80%, so the schema documents most fields. The description goes further by supplying defaults (28 steps, CFG 6), recommended resolutions, and the pass-through behavior for unknown fields, which the schema does not state.

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?

States a specific verb (Generate) and resource (NovelAI images) and enumerates the distinct modes it covers (text-to-image, img2img, infill, vibe transfer, precise reference, multi-character). This clearly separates it from siblings like novelai_encode_vibe or novelai_upscale, which handle single steps rather than full generation.

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?

Gives explicit workflow conditions: verified free requests run on the human's instruction, while paid or unknown prices require cost_approved, and high-resolution output requires separate consent. It also advises resolution selection by composition. It stops short of naming alternative tools for adjacent jobs, so it is strong but not exhaustive.

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