Audit Design System

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

Annotations already declare the tool read-only, idempotent, and non-destructive; the description reinforces this with 'Deterministic static analysis' and 'paste source,' implying no side effects and no external repo access. It adds context about the return value, including a consolidation plan, though it does not mention limits like input size or exact response structure.

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 dense sentences cover what the tool measures, when to use it, and how it relates to a sibling tool, with no filler. The output metrics are front-loaded, making the core purpose immediately clear before the use cases and comparison.

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-parameter, read-only analysis tool, this is nearly complete: input format, output highlights, use cases, and sibling differentiation are all covered. Since there is no output schema, a bit more detail on exact return shape or constraints would make it fully complete, but the description is still sufficient for correct tool selection.

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 single code parameter already has a clear schema description, including concatenating multiple files, so schema coverage is 100%. The tool description adds value beyond the schema by naming accepted formats: 'CSS / SCSS / Tailwind / JSX source,' which helps an agent know exactly what input is valid.

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 a specific verb and resource: 'Measure how systematic an existing UI really is' and enumerates concrete outputs like consistency score, color/spacing/token sprawl, near-duplicates, and off-grid values. It also distinguishes itself from design_lint by explicitly contrasting a 'whole-codebase view' with 'per-line anti-patterns.'

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?

It gives explicit trigger scenarios: 'Use it before a redesign, on an inherited codebase, or to prove a design system is (or isn't) being followed.' It also names the relevant alternative tool, design_lint, and explains how the two complement each other, giving an agent clear routing guidance.

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