Pharaoh - Your AI breaks things it can't see

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

Adds crucial behavioral context beyond readOnlyHint=true: describes detailed return format (risk score 0-1, critical/high/medium/low tiers, complexity metrics, churn data) and discloses tier limitations (Pharaoh Pro vs free preview). 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 headers (CALL THIS WHEN, RETURNS, TIER). Every section serves distinct purpose. Tier warning about 'preview' vs 'full data' is necessary for user expectations despite being commercial context.

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?

No output schema exists, but RETURNS section comprehensively describes output structure (scores, tiers, complexity metrics). Tier limitations disclosure ensures users understand data completeness constraints. Appropriate for 0-parameter analysis tool.

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?

Input schema has zero parameters, establishing baseline 4 per rubric. Description correctly requires no parameter elaboration since the tool appears to analyze the current context or entire codebase without specific inputs.

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?

Opens with specific verb 'Score' + resource 'functions' + clear concept 'regression risk — how likely a change here breaks production.' Distinguished from sibling get_blast_radius by focusing on quantified risk scoring rather than just mapping dependencies.

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?

Exceptional 'CALL THIS WHEN' section lists 4 specific contextual triggers: before modifying functions, during code review, planning refactors, and after regressions. Provides concrete workflow integration points that clearly separate it from analysis tools like search_functions or get_test_coverage.

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