athena_decision_evpi

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

With no annotations present, the description carries the full burden of behavioral disclosure. It mentions a 'declared model' but does not disclose whether the tool modifies state, what the return value looks like, how randomness is controlled, or prerequisites for 'context_key.' This is a significant gap for a decision-making tool that likely returns a value or writes to state.

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, grammatically correct sentence that front-loads the main verb and key concepts. It contains no redundant words or filler, earning its place efficiently.

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 tool's complexity (four parameters, no output schema, no annotations), a 15-word description is inadequate. The agent cannot determine what context_key references, what format actions should take, how samples and seed affect the outcome, or what the return value represents. The description is far from sufficient for reliable 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%, and the description does not explain any of the four parameters (context_key, actions, samples, seed). While 'Monte Carlo' implies the role of samples and 'declared model' hints at context_key, the semantics of actions and seed are unclear, and no guidance is provided for constructing valid inputs.

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 estimates 'expected value of perfect information' via 'Monte Carlo' under a 'Gaussian linear belief and utility model.' It uses a specific verb ('estimate'), names the exact quantity (EVPI), and differentiates from sibling tools like athena_decision_evsi and athena_decision_evi by focusing on EVPI. The method and model context are explicit.

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 provides context (Monte Carlo under a Gaussian linear model) that implies when this tool is applicable, but it does not explicitly state when to use it versus alternatives such as athena_decision_evsi or athena_decision_evi. No exclusions or alternative references are given, so guidance is only implied from the tool name and description.

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