Pharaoh - Your AI breaks things it can't see

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

Annotations indicate read-only safety; description adds valuable behavioral constraints including 'All sub-queries run in parallel server-side' and explicit 'LIMITS' section (max 5 modules, 3 searches, etc.). Does not disclose latency, caching, or permission requirements.

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 semantic headings (CALL THIS WHEN, RETURNS, LIMITS). No wasted words; every sentence provides specific guidance on capabilities, constraints, or alternatives.

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 no output schema, description comprehensively details return value ('codebase map, module profiles, search results...'), aggregation behavior, and operational limits. Complete for a zero-parameter reconnaissance 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?

Zero parameters present (baseline 4). Description appropriately omits parameter discussion since none exist, though it implies capability constraints (limits) that would typically be parameterized, potentially causing slight confusion.

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?

Description clearly states the tool 'Get[s] the full architectural picture in ONE call' and explicitly distinguishes from siblings by listing what it combines (codebase map, module deep-dives, etc.) and stating 'Use individual tools (get_module_context, get_blast_radius, search_functions, etc.) for follow-up deep-dives'.

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 explicit 'CALL THIS WHEN' section with three specific scenarios (starting tasks, reviews, when targets are known upfront) and directly names alternative individual tools for follow-up actions, providing clear when-to-use vs when-not-to-use guidance.

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