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

With no annotations provided, the description carries the burden and does communicate that this is a read-shaped operation that returns token data and embedded agent instructions, along with the rationale (visual consistency). It does not discuss any side effects or output structure beyond naming token categories, but for a read tool that is a minor gap.

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 short sentences, front-loaded with what is returned and closed with the actionable timing rule. Every clause carries information; nothing is redundant.

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 one-optional-parameter read tool with no output schema, the description says what comes back and when to call it, which is sufficient to invoke correctly. Only the absence of any note on theme/slug behavior relative to the sibling list tool leaves a small gap.

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 100% and the single `slug` parameter is already documented as a theme slug with an explicit "Omit for the default" fallback. The description adds no further meaning about slug resolution or theme selection, so the baseline 3 applies.

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?

States a specific verb ("Return") and resource ("design tokens") and enumerates the token categories included (colours, typography, radius, shadows, spacing), plus mentions agent instructions. It does not explicitly name list_design_systems as the contrasting read, so sibling differentiation is implied 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?

"Call this before composing a page" gives a clear sequencing rule that ties the tool to compose_page in the workflow. It stops short of stating when to prefer this over list_design_systems, so no alternative-selection guidance is provided.

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