athena_nonlinear_predict

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

With no annotations, the description must carry the full behavioral burden. It discloses meaningful model behavior—polynomial basis, full covariance, and OOD-dependent interval inflation—but does not state whether the operation is side-effect-free, what the output format is, or how edge cases are handled. This is partial but incomplete disclosure.

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, front-loaded sentence followed by a concise exclusion. Every word adds technical value, and there is no filler or redundant restatement of the tool name.

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?

For a tool with 7 parameters, 0% schema coverage, no annotations, no output schema, and a nested features object, this description is far too sparse. It conveys the model archetype but not enough operational detail for an agent to construct valid inputs, choose correct parameter values, or understand the return contract.

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% and no parameter is explicitly explained. The phrase 'OOD-dependent interval inflation' hints at ood_gain and target_coverage, and 'degree-2 polynomial-basis' relates to features, but required fields like regime and arm_id are entirely unaddressed. The description provides only weak semantic clues rather than usable parameter guidance.

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 a 'Degree-2 polynomial-basis Bayesian prediction' with specific technical traits (full-covariance V5 posterior, OOD-dependent interval inflation), and it explicitly differentiates itself from 'GP/neural universal inference.' This makes the tool's purpose and scope distinct from sibling prediction tools.

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 only usage guidance is the negative statement 'Not GP/neural universal inference,' which implies when not to use it but provides no explicit alternatives or when-to-use conditions. The intended use is implied by the model name and technical description, but an agent is not given clear selection criteria among the many sibling prediction tools.

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