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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by specifying exactly what data is exposed (light and dark values, StyleX aliases, raw groups), which helps set expectations beyond the empty parameter schema.

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 dense sentence front-loads the main subject and then lists the included categories with no filler. Every phrase adds information about what the tool returns.

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 zero parameters, a rich output schema, and comprehensive annotations, the description fully covers the invocation context. An agent knows exactly what this tool provides and can safely call it without additional guidance.

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?

The input schema has zero parameters, so the description need not explain parameter meaning. The baseline of 4 applies; the description still adds value by clarifying the scope of the returned token data.

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 states the specific resource (design tokens page) and enumerates its contents: CSS custom properties, light/dark values, StyleX aliases, and raw token groups. This clearly distinguishes it from sibling get_* tools like get_component and get_guide without needing to inspect schemas.

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 intended use is implied: call this when design tokens or CSS custom properties are needed. However, there is no explicit when-to-use guidance or mention of alternatives, even though similar siblings exist. The description makes the use case obvious but leaves routing to inference.

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