Generate a design-token set (palette / motion / layout)

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

With no annotations provided, the description carries full burden. It discloses deterministic generation, OKLCH harmonization, WCAG contrast ratios, and Material-Motion-derived durations, which gives insight into behavior beyond simple generation. It does not explicitly state side-effect-free behavior, but 'generate' implies no mutation, and the lack of side-effect warnings is acceptable.

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 two sentences that are information-dense yet concise. It front-loads the core purpose and immediately follows with usage constraints, with no filler or repetition of schema details.

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 tool has no output schema, but the description enumerates the token categories returned, effectively compensating for missing return documentation. It also covers input options and the ordering requirement relative to riv_create. Minor gap: no mention of how results are returned (e.g., JSON structure), but the listing of token types provides sufficient context for a generation tool.

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 67% and the description adds meaning by listing the allowed mood values, scheme options, and optional seed color. It contextualizes how these parameters affect generation (mood as hue default, seed as optional brand color), going beyond the raw enum/pattern definitions.

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 design tokens deterministically for a scene, listing specific token categories (palette, gradients, motion, spacing, type scale). It also explicitly positions this as a prerequisite step before riv_create, distinguishing it from sibling tools.

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 explicitly instructs to call this first and to use only the returned values in the scene spec, never inventing raw hex colors or ad-hoc durations. This provides clear when-to-use guidance and an explicit alternative/ordering relative to riv_create.

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