Exam Eye Score

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

With no annotations, the description carries the full burden, and it does disclose the decision rule (beat chance at p < 0.05 means the test is compromised). However, it says nothing about whether scoring mutates stored state, whether a run can be repeated, or what permissions are needed.

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?

Two short sentences, front-loaded with the step identity and the verdict rule; the explanatory clause about why leakage matters earns its place by justifying the verdict. Tight 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?

The output schema covers return values and the description covers the decision rule, so the result side is adequate. The input side is not: with zero schema coverage on a nested object parameter and no annotation coverage, an agent can't confidently construct 'out' or 'answers' from this text alone.

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% for two required parameters, one of them a free-form nested object. The description hints that 'answers' holds the picks from the prior crop step, but 'out' is completely unexplained, and there is no shape or format guidance for the nested payload.

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 text uses a concrete verb ('score') and names the artifact being scored ('your picks from exam_eye_crops') along with the reference ('the hidden key'), so the operation is identifiable. It also implicitly separates itself from exam_picture_score by being the crop-based ('eye') variant, though it never states that contrast outright.

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?

'Step 2' with an explicit dependency on exam_eye_crops tells the agent when this tool is applicable, and the 'NOT READY when you beat chance (p < 0.05)' clause tells it how to act on the outcome. It stops short of stating exclusions or what to do if the prerequisite step was skipped.

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