Pharaoh - Your AI breaks things it can't see

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

Annotations declare readOnlyHint=true; description adds valuable behavioral context beyond safety: details return structure (components with props/usage counts, tokens, anti-patterns) and important scope limitation (screen/page components excluded by default). Does not mention performance characteristics or caching behavior.

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?

Excellent structure with clear visual hierarchy: main directive, CALL THIS WHEN, RETURNS, EXAMPLES, and WHY NOT sections. Every sentence earns its place; examples are concrete and relevant. No redundant repetition of schema or annotation data.

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?

Highly complete for a parameter-free tool. Compensates for missing output schema by explicitly detailing what the tool returns (components, tokens, anti-patterns) and what it excludes. Complexity is appropriate for the tool's scope.

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?

Zero parameters present; schema is empty object. Baseline score of 4 applies as per rules for parameter-free tools. No parameter documentation needed.

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?

Excellent specificity: verb 'discover' + resource 'design system' + clear scope (components, tokens, anti-patterns). The description clearly distinguishes this from general codebase analysis tools like get_codebase_map by focusing specifically on UI components and design tokens.

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?

Outstanding guidance with explicit 'CALL THIS WHEN' section listing 4 specific scenarios (creating React/Vue components, finding canonical patterns, locating tokens, detecting anti-patterns). Includes 'WHY NOT JUST READ FILES' section explaining when to use this tool versus manual file exploration.

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