Pharaoh - Your AI breaks things it can't see

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

The description mentions mutation actions (Toggle PR Guard, trigger graph refreshes, manage billing) which aligns correctly with readOnlyHint=false. It also notes the ability to open the visual dashboard externally, adding context beyond the annotations. Does not mention rate limits or auth requirements, but annotations cover the safety profile (destructiveHint=false).

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 the core purpose front-loaded in the first sentence, followed by the explicit 'CALL THIS WHEN' directive. While the bullet list is lengthy, each item represents a distinct use case that helps the LLM route correctly among the 20+ sibling tools. No wasted sentences.

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?

Given the tool handles multiple account functions (billing, PR Guard, graph refresh) with no output schema, the description adequately covers the functional scope. It could benefit from hinting at return structure (e.g., 'returns subscription details'), but the comprehensive use-case coverage compensates.

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 (empty properties object). Per calibration rules, 0 params = baseline 4. The description appropriately does not invent parameters, implying the tool manages state contextually or interactively.

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 opening sentence uses specific verbs (View, manage, Toggle, trigger) with clear resources (subscription status, billing, PR Guard, graph refreshes). It effectively distinguishes from siblings—all other tools are code analysis functions (get_codebase_map, search_functions, etc.), while this is explicitly the account/billing management interface.

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 7 detailed bullet points covering subscription checks, payment updates, plan verification, PR Guard toggling, graph refreshes, and dashboard access. This provides explicit routing guidance for when to select this tool over the code-analysis siblings.

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