Pharaoh - Your AI breaks things it can't see

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

Superb. Annotations only state readOnlyHint=false/destructiveHint=false. Description adds critical operational context: single-use URL with 10-minute expiration, exact data transmitted (structural metadata only), agent execution responsibilities ('execute this bash block directly'), and requires user approval. Privacy disclosure ('Source code never leaves') is crucial behavioral context.

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 three distinct sections: purpose/privacy guarantee, usage conditions with bullet points, and execution instructions. Front-loaded with clear verb. No redundant text; complex operational details (expiration, single-use, local parsing) are essential.

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?

Thorough despite no output schema. Description compensates by detailing return value format ('ready-to-run bash block'), side effects (repo mapping), authentication needs (user approval), temporal constraints (10-minute expiry), and data handling policies. Covers all operational gaps.

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?

Baseline 4 for 0 parameters. Input schema is empty object. Description mentions 'When path is provided' which appears to reference a parameter not defined in schema, potentially causing confusion, but with zero parameters there is no schema documentation to supplement.

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?

Excellent. States specific action ('Map a local repo into Pharaoh'), identifies the resource (local repo), and distinguishes from sibling workflow ('without installing the GitHub App'). The privacy guarantee ('Source code never leaves the machine') further clarifies the scope.

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. Explicit 'CALL THIS WHEN:' section with four specific bullet points includes trigger phrases ('analyze this repo'), references sibling tool get_codebase_map for conditional logic, and identifies target scenarios (private repos without admin access). Clear differentiation from GitHub App installation path.

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