Recommend Incrementality Tests

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behavioral context: the auth scope required, the backend capability gate, explicit exclusion of missing posteriors, the meaning of limited_variance_contraction vs posterior_variance_expanded, and the disclaimer that cross-channel dependence is not modelled and test history is unavailable. This is well beyond what the annotations provide and contradicts nothing.

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?

Purpose is front-loaded correctly, but the middle is a dense run-on enumerating return keys and warning codes that the output schema already carries, producing a wall of text where a shorter semantic gloss would suffice. Every clause is informative but the listing is not optimally sized.

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?

Covers auth requirements, backend gating, exclusion behavior, score interpretation and known modelling limitations, so an agent can judge appropriateness. It leans on prose to restate return fields already in the output schema and omits any meaning for model_hash, which slightly undercuts completeness.

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?

With 0% schema coverage the description must compensate, and it does for three of four params: limit is bounded 1-50, budget is a positive exposure scale defaulting to current spend, and hurdle is the non-negative marginal-return alternative defaulting to 1. model_hash, the only required parameter, is never explained, leaving one gap.

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?

Opens with a specific verb+resource+basis: 'Rank channels for experiment investigation using stored posterior marginal returns.' It also contrasts itself against siblings by stating it does 'no fit, test creation or budget changes', which separates it from create_incrementality_test and run_pipeline without opening their schemas.

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?

States the read-only framing and that it requires read:results and backend support for test-priorities, which tells the agent when the call can succeed. It implies but never explicitly names the alternative (create_incrementality_test) or the condition that selects it, so routing is left partly to inference.

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