Build a design system

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with that (it computes and exports, it does not persist). It adds useful behavioral detail beyond annotations: exactly what artifacts are produced and that a contrast audit is included. It stops short of describing return shape or limits, which keeps it off a 5.

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?

A single front-loaded sentence that opens with the core action and then lists outputs; no filler or repetition. The dense enumeration is justified by the tool's breadth, though the run-on form makes it slightly harder to scan than a short multi-sentence layout.

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 output schema, the description carries the return-value burden and does so well by naming every deliverable (scales, theme roles, four export formats, contrast audit). The remaining gap is that it does not clarify how optional color inputs (accent, neutral, secondary) affect the output when omitted.

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 57%, and the description meaningfully expands the 'format' enum by naming Tailwind v4, CSS variables, shadcn/ui globals.css and DTCG tokens, plus the 50–950 scale structure. It says nothing about name, primary, secondary, accent, neutral or the 'values' enum, leaving several parameters documented only in the schema.

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?

Specific verb ('Build') plus a precisely scoped resource ('full color system from a brand color'), enumerating the 50–950 scales, five color families, theme roles, export formats and the contrast audit. This scope clearly separates it from narrow siblings like generate_palette, generate_scale and export_tokens.

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?

Usage is implied by the breadth of the output (a whole system rather than one palette), so an agent can infer it is the heavyweight option. However, it never states when to prefer this over generate_palette/export_tokens or any prerequisite, so no explicit guidance is given.

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