Pharaoh - Your AI breaks things it can't see

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

Annotations cover safety (readOnly: false, destructive: false), while the description adds valuable outcome context ('Your feedback directly improves result quality'). It explains the 'WHY' behind the tool's existence, though it could enhance further by describing the feedback mechanism (e.g., whether it's batched, immediate, or triggers notifications).

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?

Perfectly structured with three distinct sections: opening condition statement, bulleted triggers ('CALL THIS WHEN'), and value proposition ('WHY'). Every sentence serves a distinct purpose. No redundancy with structured fields (title/annotations). Appropriate length for complexity.

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?

For a feedback utility with no parameters and no output schema, the description is complete. It covers invocation triggers, expected content, and value proposition. No gaps exist given the tool's simplicity; the agent understands exactly when and why to invoke this 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 contains 0 parameters, setting baseline 4 per evaluation rules. The description mentions including specific content ('dead_code_report') which contextualizes how to use the parameterless tool, though without explicit parameters in the schema, no additional semantic mapping is required or provided.

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 clearly defines the tool's purpose using specific verbs ('Call this', 'Submit') and identifies the resource (feedback). It distinguishes itself from siblings by referencing specific tools like 'get_unused_code' and scenarios like 'A search returned no results' that map to other tools in the server (search_functions), effectively differentiating when to use feedback versus direct tool invocation.

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?

Excellent explicit guidance via 'CALL THIS WHEN:' bullet points covering empty results, missing information, positive reinforcement, workarounds, and specific false positives from get_unused_code. It provides concrete trigger conditions and even specifies what content to include ('include dead_code_report'), giving clear alternatives to using other tools.

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