Plan Reward Hacking Guardrails

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

The description aligns with the 'readOnlyHint': true annotation, confirming no side effects. It adds value by enumerating specific patterns detected, which goes beyond the annotation. However, it does not describe any additional behavioral traits like performance or data requirements.

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?

The description is a single concise sentence that lists clear patterns, with no redundant information. It is front-loaded and 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?

While the description explains the tool's purpose and detection scope, it omits details about the output format (e.g., whether it returns a boolean, report, or risk score) and how to interpret results. Given the lack of an output schema, this is a notable gap.

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 coverage is 100% with all parameters described. The description does not add specific parameter-level details beyond the schema, so it meets the baseline. The overall tool purpose helps contextualize the parameters but does not enhance their semantics.

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 states the verb 'detect' and the specific resource 'reward-hacking patterns,' listing distinct types. This differentiates it from sibling tools like 'plan_proactive_agent_eval_guardrails' or 'verify_claim' which focus on different aspects.

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?

The description implies usage for detecting reward hacking but does not explicitly state when to use this tool over alternatives. No guidance on prerequisites, when not to use, or comparison with siblings like 'verify_claim' or 'plan_proactive_agent_eval_guardrails' is provided.

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