Mne Decoding Group Test

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

With no annotations, the description carries the disclosure burden and does so thoroughly: it states the statistical model (sign-flip permutation, symmetric-effects null), the two correction methods, and the outputs ('statistic, corrected p values or cluster p values, mask, H0 and diagnostics'). It also notes that it is group-level, not single-subject or prevalence inference, making behavioral scope clear.

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 dense but well-front-loaded block; the first clause states the purpose and every following clause covers a distinct requirement, method option, assumption, or output. It could be restructured with bullets for readability, so it stops short of 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?

For a statistically complex tool, the description is complete: it covers prerequisites, forbidden input patterns, supported metrics, correction methods, null-hypothesis assumptions, and stored outputs. The rich input/output schemas cover structured details, so nothing necessary 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?

The schema already documents every parameter at 100% coverage, so the baseline is 3. The description adds useful cross-parameter semantics: null_value is predeclared and usually 0.5, score_names must be one mean result per independent subject, and matching time grids/methods are supported. This nudges the score above baseline.

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 opens with a specific verb-resource pair: 'Group-level sign-flip inference on mne_decode mean scores, one per independent subject.' It also explicitly excludes what it is not ('Not single-subject label shuffling or population prevalence'), which differentiates it from sibling tools such as mne_decode in one line.

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?

It gives explicit conditions for use: score_names, unique subject_ids, independent_subjects=true and explicit null_value. It gives a hard negative rule, 'Never pass CV folds or repeated runs as subjects,' and clarifies that this is not single-subject label shuffling or population prevalence, so an agent knows when to avoid it.

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