athena_pareto_bandit_select

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

With no annotations provided, the description carries the burden of disclosing behavior. It explains the two-step process (identify frontier, then choose candidate) and the constraint that it is only for experiment selection. Yet it does not disclose whether the operation is read-only, what side effects or mutations occur, what the return value is, or any permissions needed. This is a moderate gap given the absence of annotations.

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 two sentences and front-loads the main purpose. The first sentence clearly states the action, and the second adds a strong scope constraint. It is concise, though 'EXPERIMENT_SELECTION_ONLY' is partly redundant with 'choose ... for experimentation' and adds a tone that could be clearer without the capitalization.

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?

For a tool with three parameters, a nested object schema, and no output schema, the description is too sparse. It doesn't explain what inputs are needed, how to structure candidates, what 'interval-possible' means, or what the output looks like. The agent cannot reliably invoke this tool without additional schema descriptions or examples, so completeness is low.

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 provides no explanation of the three parameters (candidates, directions, exploration_weight). The agent gets no guidance on what the candidates array should contain, what directions means, or how exploration_weight behaves. The description's mention of 'Pareto frontier' and 'uncertainty-rich' is too vague to compensate for the complete lack of parameter documentation.

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 what the tool does: it identifies an interval-possible Pareto frontier and selects an uncertainty-rich candidate for experimentation. The phrase 'EXPERIMENT_SELECTION_ONLY' reinforces the selection-specific scope, which helps differentiate it from tools that compute frontiers or perform other bandit operations. However, the term 'interval-possible' is jargon and the description doesn't explicitly contrast with sibling tools like athena_pareto_frontier or athena_bandit_select.

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 explicitly scopes usage with 'EXPERIMENT_SELECTION_ONLY', making it clear this tool is for experiment selection rather than general Pareto or bandit analysis. It states when to use it (for selecting a frontier candidate) and implicitly when not to (anything outside experiment selection). It does not, however, name alternative tools for other tasks, which would make the guidance fully explicit.

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