athena_joint_policy_robust

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool computes (ranking policies) but does not state whether it is read-only or has side effects, what the output format is, or any computational caveats. The 'PLAN_ONLY' hint is vague and does not clarify potential behavior.

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, about 20 words, that front-loads the primary action and then lists the ranking criteria. It is efficient but 'PLAN_ONLY' is cryptically appended, which slightly hurts clarity. Still, it earns its place without wasted wording.

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?

Given the complexity (6 parameters, no output schema, no annotations), the description is insufficiently complete. It does not explain key concepts like 'bounded weighted joint-state ensemble', parameter relationships, or expected return format. The tool's rich sibling context (e.g., policy_score, pareto_frontier) is not addressed, leaving the agent without enough context to ensure correct invocation.

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 description coverage is 0%, so the description must compensate for the lack of parameter documentation. While it lists criteria like 'lower-tail CVaR' and 'expected/max regret', it does not explicitly map these to the parameters (e.g., cvar_alpha, cost_weight, risk_weight, regret_weight). The meaning of cost_weight and risk_weight remains ambiguous, leaving a significant gap.

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 tool's action: 'Rank policies' over a 'bounded weighted joint-state ensemble', specifying multiple ranking criteria. This is specific and likely distinguishes it from other policy tools, though it doesn't explicitly name any sibling alternatives.

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 use of 'PLAN_ONLY' provides a contextual constraint, implying this is for planning-phase analysis only. However, there is no explicit guidance on when to use this tool versus alternative policy-ranking or evaluation tools, and no mention of exclusions beyond the planning context.

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