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

Annotations already mark it read-only and side-effect free, and the description goes well beyond that: it explains what is returned (share of margin explained by search, what pure noise would give, whether the excess is real) and the conditional behavior when n_per_variant is supplied. This is rich behavioral context beyond the structured fields.

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?

Front-loaded with the trigger condition and the mechanism, and most sentences carry information. Minor padding in the 'FREE.' lead and the rhetorical framing keeps it from being maximally tight.

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?

There is no output schema, so the description bears the burden of explaining returns — and it does, describing the three quantities produced. Combined with the usage trigger and the optional-parameter effect, nothing essential for correct invocation is missing.

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 100%, so the baseline is 3, but the description adds real meaning: it says n_per_variant reveals whether variants are distinguishable at all, which the schema's 'Trials behind each score' does not convey. The scores parameter's semantics are largely left to the schema.

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 purpose: quantifying how much of a selected winner's margin is explained by the search itself, versus noise. An agent can tell this is a selection-bias correction tool, but the description never names or contrasts with close statistical siblings such as multipletest or deflatedsharpe.

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?

Gives clear triggering context ('Use after picking the best of several prompts, models, configs or hyperparameters') and an explicit guardrail ('Call this before concluding an optimisation found something'). No alternative tool is named for the case where the user hasn't run a selection procedure, so it stops short of 5.

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