aetre_exploration_audit

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 discloses that it calculates an estimator and confidence intervals, but it does not state whether the operation is read-only, any side effects, or the output format. It also fails to mention the required api_key parameter, leaving the agent unclear about access requirements. This is a notable gap for a tool with no annotation support.

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 sentence that efficiently conveys the core computation and purpose, front-loading the main action. The technical terminology (e.g., Horvitz-Thompson estimator) is specific but may require domain knowledge, yet the structure is clean and waste-free.

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 is a statistical calculation with three required numeric inputs and no output schema, the description should at least state what the function returns (e.g., the estimate and confidence interval). It does not, nor does it mention the api_key field. While the purpose is clear, the lack of output details and access requirements makes it only minimally complete.

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?

The input schema provides complete descriptions for all four parameters (deprioritized_pool_size, audited_sample_size, audited_high_value_found, and api_key), so the schema already covers parameter semantics. The description adds no additional guidance about parameter relationships or constraints, so it is at the baseline for high schema coverage.

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 a specific action ('Calculates'), a specific resource ('unbiased Horvitz-Thompson exploration audit estimator (H_hat_D)'), and the purpose ('to catch false negative breakthroughs'). It distinguishes this tool from sibling tools like aetre_calculate_voi by focusing on auditing deprioritized candidates, which is a unique function.

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 when to use the tool (when auditing deprioritized candidates), but it does not explicitly state conditions, alternatives, or exclusions. There is no mention of prerequisites like the api_key or when not to use it, so usage guidance is only implied by the purpose.

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