Pharaoh - Your AI breaks things it can't see

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

While annotations declare readOnlyHint=true/destructiveHint=false, the description adds significant operational context: it discloses the cross-referencing algorithm ('cross-references the entire spec tree against the function graph'), performance characteristics ('gaps that would take an hour to find manually surface in seconds'), and business-tier constraints ('Pharaoh Pro — free tier receives a preview'). It does not disclose specific complexity thresholds or rate limits, preventing a 5.

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?

The description is well-structured with clear visual headers (CALL THIS WHEN, RETURNS, EXAMPLES) that facilitate parsing. It is front-loaded with the core purpose. While lengthy, the EXAMPLES section (4 queries) and tier warning earn their place by clarifying intended use cases and business constraints. Minor redundancy exists between the bullet points and examples, preventing a perfect 5.

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?

Despite lacking an output schema, the description thoroughly documents return values: 'Two lists' with specific fields (function names, complexity scores, file paths, spec references). It also explains the tier-based limitation (preview vs. full data) which affects the output. For a complex analysis tool with zero parameters, this provides sufficient completeness, though specific complexity thresholds could have been mentioned.

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 contains zero parameters. Per calibration rules, 0 params yields a baseline score of 4. The description appropriately requires no parameter clarification since the tool operates as a global analysis requiring no filters.

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 opens with a specific dual-purpose statement: 'Find what's missing — specs without code AND complex code without specs.' This clearly defines the tool's unique value proposition (bidirectional gap analysis) and distinguishes it from siblings like get_vision_docs (which likely just retrieves documents) or get_codebase_map (structural overview). The scope is precisely bounded to spec-to-code alignment.

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?

Contains an explicit 'CALL THIS WHEN' section with four specific scenarios (planning work, finding undocumented functions, auditing alignment, answering 'what's left'). Critically, it includes 'WHY NOT JUST READ FILES' which explicitly contrasts the tool against the manual alternative, demonstrating when NOT to use manual file reading. This provides clear contextual guardrails for tool selection.

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