Pharaoh - Your AI breaks things it can't see

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

Annotations declare read-only safety (readOnlyHint=true), so description adds value by detailing return structure ('path from entry point to function', 'classification') since no output schema exists, and disclosing tier constraints ('free tier receives a preview') that affect behavior. No contradictions 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?

Well-structured with clear visual hierarchy: purpose statement, CALL THIS WHEN bullets, RETURNS specification, and TIER notice. Each section earns its place, though the Pharaoh Pro marketing language ('free tier receives a preview') is slightly verbose compared to purely technical descriptions.

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?

Complete for a zero-parameter analysis tool. Compensates for missing output schema by describing return values (reachability boolean, path, classification). Tier limitation disclosure is essential contextual data. Sufficiently distinguishes from sibling analysis tools via specific 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, triggering baseline 4 per rules. Schema is '{}' (empty object), and description appropriately avoids mentioning parameters since none exist. Schema coverage is trivially 100% with no params to document.

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?

Specific verb ('Check') + resource ('functions') + precise scope ('from production entry points'). Explicitly lists entry point types (API endpoints, CLI, cron, etc.), clearly differentiating from siblings like 'get_unused_code' (which finds dead code without path analysis) and 'get_codebase_map' (general structure).

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?

Excellent 'CALL THIS WHEN:' section with four specific scenarios (post-feature implementation, PR review, dead code cleanup, pre-PR checks). Provides clear contextual triggers. Lacks explicit 'when-not' or named alternative tools to earn a 5, but the scenario specificity strongly implies appropriate usage contexts.

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