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

No annotations are provided, so the description carries the burden of explaining behavior. It communicates that the tool exposes theme-related information and adds the useful behavioral note that retheming propagates when token names are used. However, it does not clarify the return format, whether this is purely read-only, or any limitations such as which token categories are included.

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 short sentences with no filler. It front-loads the tool's subject ('the theme system'), then lists the specific content areas, and closes with a practical usage rule. Every clause contributes meaningful information.

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 simple no-parameter, no-output-schema getter, the description provides enough context to understand what the tool offers: relevant hooks and design scales, plus guidance on using token names. It lacks an explicit statement of what exactly the tool returns and doesn't mention color tokens, but given the minimal complexity, it is reasonably complete.

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 tool has zero parameters and the schema coverage is effectively 100%, so there is nothing for the description to add about parameters. This matches the baseline for a no-parameter tool, and the description appropriately focuses on result semantics instead.

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 identifies the tool's domain—theme tokens—and specifies what it covers: hooks to call and spacing, radius, and typography scales. It avoids tautology, but it never uses an explicit verb like 'retrieves' or 'returns,' relying on the tool name for the action, and it doesn't explicitly distinguish itself from sibling getter 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 implies the tool is relevant when working with the theme system, but it does not state when to use get_theme_tokens versus alternatives like get_rules or get_provider_tree. The instruction to reference token names rather than hex values is useful post-retrieval guidance, but it doesn't address tool selection or conditions for use.

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