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

Annotations already declare readOnlyHint, idempotentHint, and a closed world, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the return shape is CSS custom properties (var(--color-primary)) and the prefix argument narrows the result set. It stops short of noting ordering or result size, so not 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?

Two compact sentences, with the core purpose front-loaded and the parameter behavior second. The clause 'never a color written out' is slightly idiomatic but still earns its place as a usage directive.

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 zero-required-parameter read tool with no output schema, the description supplies the two things an agent needs: the output format and the filtering behavior. Only minor gaps remain (behavior with no prefix, result ordering), which are low-stakes here.

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 carry the parameter, and it does: the prefix argument 'gives only those' and the examples (--color-, --radius-, --text-) show the expected literal form including the trailing hyphen. That is meaningful guidance the bare schema pattern does not convey, though it doesn't clarify whether matching is a raw string prefix or a semantic group.

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 resource precisely ('The design tokens as CSS custom properties') and the annotation title supplies the read verb, so the agent knows it retrieves design tokens. It is clearly distinguishable from the sibling set (blocks, charts, pages, rules, components), none of which return 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?

'For your own CSS: var(--color-primary), never a color written out' gives the intended use case — pulling token names to reference instead of hardcoding colors. However, it never states when to call it versus any alternative, nor what happens when the prefix is omitted (presumably all tokens), 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.