verify_model_gap

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds valuable behavioral context by explaining the statistical interpretation (real vs. below test-set resolution) and the specific outputs returned, which goes beyond the structured 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 concise, front-loaded sentences. The first sentence frames the decision, and the second gives direct input/output instructions. There is no filler or redundant elaboration.

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?

The description covers purpose, required inputs, and high-level outputs, while the output schema handles detailed return structure and annotations cover safety. It could explicitly state assumptions such as using the same test set or the statistical test employed, but for a read-only verification tool with strong schema coverage, it is sufficiently 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?

Schema coverage is 100%, with clear descriptions for every parameter: n as items per model, p1/p2 as accuracies in [0,1], and api_key as a metering key. The description's input guidance ('items-per-model n and the two accuracies') simply restates what the schema already provides, adding no new semantic detail.

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 opens with a question that defines the exact purpose: determining whether an accuracy gap between two models is real or below test-set resolution. It names the required inputs (n, p1, p2) and the outputs (gap, significance, minimum detectable effect), and it clearly distinguishes this tool from sibling verify_* tools that target backtests, judges, or receipts.

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 question-format clearly frames when to use the tool: when you have two model accuracies and items-per-model counts and need to know if the gap is meaningful. It gives direct instructions for inputs, but it does not explicitly mention when not to use it or name alternative sibling tools, so it stops short of full guidance.

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