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

Annotations already declare readOnly, idempotent, closed-world, so the safety profile is covered. The description adds genuine content-shape context the annotations cannot: the dark value is always present, the light value only appears where it differs, and tokens follow the user's color mode. It appropriately omits return formatting because an output schema exists.

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?

Two sentences, front-loaded with the resource and its groups, then the var(--name) usage rule; nothing repeats the name or title. The middle clause about dark/light values is slightly tangled with its em-dash aside but still earns its place.

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 an output schema handling return shape, 100% parameter coverage, and annotations covering the safety profile, the description supplies what remains: what the tokens are, how they are grouped, and the dark/light mode behavior. The only real omission is any hint that a category filter exists.

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 the optional case-insensitive 'category' parameter is fully documented in the schema, which sets the baseline at 3. The description never mentions that results can be narrowed to one group — it only says tokens are 'grouped' — so it adds no meaning beyond the schema and slightly implies an always-full listing.

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 names the precise resource — DRYL's CSS custom properties — and enumerates the groups (colors, glass, accent, spacing, radius, motion), which is far more specific than the title. It is unmistakably different from get_component or validate_markup, though the retrieval verb itself is implicit rather than stated.

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 only guidance is downstream usage — 'Reference these with var(--name) in your CSS instead of writing literal colors' — which tells the agent what to do with the output, not when to call this tool versus get_component. There is no explicit trigger condition or exclusion, so usage is only implied.

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