verify_retrieval

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

Discloses key behaviors: uses independent Coach LLM, never raises exceptions (returns LOW with error), returns confidence levels and claim lists. No annotations, so description carries burden well, though could mention idempotency.

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?

Three concise sentences with front-loaded purpose and no fluff. Version number is minor but acceptable.

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 main behavior and return structure given no output schema. Could add more detail on return format (e.g., type of lists) but sufficient for most use cases.

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?

Schema covers 100% of params. Description adds value: 'Missing IDs are silently dropped' for fact_ids and default model info for verification_model.

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 uses specific verb 'verify' and resource 'answer grounded in facts', with unique approach 'Adversarially' and 'Coach LLM'. It clearly distinguishes from sibling tools like find_contradictions.

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?

Implied usage for thorough verification, but no explicit when-to-use or when-not-to-use guidance compared to alternatives like find_contradictions or query_fact.

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