verify_prediction

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

With no annotations, the description carries the full burden and does substantial work: it enumerates the verdict values, the exit_code meanings (0 PROCEED / 3 human check / 2 BLOCK), and a strong fail-closed contract (misaligned/wrong-length input refused, ERROR maps to BLOCK). It omits auth requirements and idempotency, but the safety-critical behavior is unusually well disclosed.

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?

Dense and front-loaded with 'THE GATE' before the mechanics, with every clause conveying a distinct fact (returns, exit codes, fail-closed policy). The terse fragments are economical, though the shorthand is jargon-heavy for a reader without domain context.

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?

With no output schema and no annotations, the description must explain results itself and does so (verdict, R^2, coverage, kappa, exit_code). The main remaining gap is that it doesn't explain how predictions are sourced or what scenario_key identifies, which matters for a 2-param submission tool.

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 only 50% and scenario_key is documented nowhere. The description does compensate partially by tying 'only when y_std is supplied' to the optional y_std field and by flagging wrong-length submissions, which reinforces the array-ordering/aligned-length requirement on predictions, but scenario_key remains unexplained.

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?

States a specific verb (score/verify) and resource (predictions against a published held-out set whose ground truth is server-held), making the operation concrete. It doesn't reference the sibling get_held_out_template that an agent would need to obtain predictions in the first place, so differentiation from siblings is implicit rather than 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 implies the tool is the scoring gate you run on submissions, and the exit_code semantics hint at the follow-on decision flow, but it never states when to use this versus alternatives or any prerequisite ordering (e.g., fetch the template first). Usage is inferred, not specified.

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