Generate Design Tokens

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint safety traits. The description adds meaningful behavioral context by stating it is 'Deterministic — outputs code, not advice,' which clarifies it does not produce opinions or partial recommendations. No contradiction with annotations.

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?

Three sentences: the first front-loads the core transform and output formats, the second adds a key behavioral trait, and the third gives the primary use case and a related pairing. Every sentence earns its place with no fluff.

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?

Given there is no output schema, the description leaves the return structure unspecified — an agent may not know whether the generated 'artifact files' come back as inline strings, a zip, or a structured mapping. It also does not mention that 'format' defaults to 'all' or supports selective output. For a 7-parameter tool producing multi-file output, this is a notable gap, though the rich input schema and clear purpose mitigate it.

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 schema alone documents all parameters with examples and defaults. The description adds modest value by mapping the abstract format enum to real-world outputs ('Tailwind v4 @theme', 'SwiftUI', 'Jetpack Compose', 'W3C DTCG JSON') and grouping the optional scales, but this is marginal beyond the schema.

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 states a specific verb ('Turn ... into') and a concrete resource ('a design-token spec'), then enumerates the exact artifact formats produced. It distinguishes itself from sibling generators like generate_color_system or generate_type_scale by emphasizing multi-platform, ready-to-use files and 'one source of truth across web, iOS and Android.'

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 gives a clear use case ('give a project one source of truth across web, iOS and Android') and suggests pairing with audit_accessibility to verify contrast. However, it does not explicitly state when to avoid this tool in favor of more targeted generators like generate_type_scale or generate_color_system, so it lacks explicit exclusions.

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