athena_evidence_dependence_probability

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

With no annotations, the description must carry the safety/behavioral burden. It discloses that the model is 'caller-declared' (vs fitted) and that it is diagnostic, which is useful. But it does not state whether the tool is read-only, what side effects (if any) exist, what the output format is, or how failures are surfaced.

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 sentences, front-loaded with the action, and contains no filler. It is appropriately concise, though it sacrifices necessary detail for brevity, so it is not a perfect 5.

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 specialized statistical tool with 4 parameters, a nested object, no output schema, and no annotations. The description gives only a high-level purpose and a diagnostic caveat. It is far from complete: it lacks parameter semantics, expected outputs, error conditions, and guidance relative to the many sibling dependence tools.

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 the description provides almost no parameter-level detail. Terms like 'caller-declared logistic model' vaguely hint at 'coefficients', but claim_id, dimensions, coefficients, and min_confidence are all unexplained. An agent cannot correctly construct the coefficients object or know what min_confidence does.

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 states the action ('Apply... model') and the target ('science-shadow witness pairs'). It also adds a useful qualifier ('Diagnostic, not formal independence inference') that helps distinguish this from a formal test. However, it doesn't explicitly say the result is a probability, relying on the tool name for that key semantic.

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 phrase 'Diagnostic, not formal independence inference' provides a when-not-to-use warning and implies a diagnostic context. However, it does not name alternative tools or mention concrete scenarios where this should be preferred over siblings like athena_evidence_dependence_fit or athena_evidence_dependence_observe.

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