athena_ood_score

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 mentions the algorithmic approach (ridge-regularized Mahalanobis geometry, unseen-feature pressure) but does not disclose whether the operation is read-only, what output format is returned, whether it requires any special permissions, or any side effects. This is insufficient for a scoring tool where safety and return details matter.

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, dense sentence that front-loads the operation ('Score a context') and packs the algorithm details efficiently. There is no redundant wording, and it is appropriately sized for the information conveyed.

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?

This is a complex statistical tool with 4 parameters (including a nested object), no output schema, and no annotations. The description omits return value format, parameter details, usage context, and any behavioral caveats. For such a tool, the description is severely incomplete and would leave an agent guessing about invocation details.

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%, so the description must compensate. It implicitly maps 'context' to the features parameter and 'regime distribution' to the regime parameter, but it does not explain the 'ridge' or 'scope' parameters. The reference to 'ridge-regularized' hints at the purpose of the ridge parameter but does not define it; 'unseen-feature pressure' is ambiguous. With four parameters and no schema descriptions, this is inadequate.

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 identifies the tool as a scoring operation for context against an empirical regime distribution, using a specific algorithm (ridge-regularized Mahalanobis geometry plus unseen-feature pressure). It includes a specific verb ('score'), a resource ('context'), and a method, making the purpose unambiguous and distinguishable from generic observability or prediction siblings.

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 provides no explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. It simply states what the tool does, leaving the agent to infer usage context. No alternative tools are named or compared.

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