eval_hallucination

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

No annotations exist, so description carries full burden. It describes return format but does not disclose if it makes external API calls via judge_model or any side effects, permissions, or rate limits.

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?

Front-loaded purpose, concise arguments and returns sections. Could be slightly tighter if output schema were present, but overall efficient.

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?

Covers purpose, parameters, and return structure, but lacks usage guidance and behavioral context. Given medium complexity and available output schema, gaps remain.

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?

Adds clear explanations for each parameter beyond the schema (e.g., 'The LLM output to check', 'Provider:model for the QAG judge'), compensating for zero schema description coverage.

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?

Clearly states it detects fabricated information not in context. Differentiates from siblings by naming hallucination detection but does not explicitly compare to eval_faithfulness or others.

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?

Provides score interpretation but lacks guidance on when to use this tool versus alternatives like eval_faithfulness, and no exclusions or prerequisites.

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