Compare sample means by running one-sample, two-sample, or paired t-tests with optional one-sided alternatives; accepts inline samples or @path file references.
Run a one-sample, two-sample or paired t-test with an optional one-sided alternative.
Samples may be passed inline or as an ``"@<path>"`` file reference.
| Name | Required | Description | Default |
|---|---|---|---|
| paired | No | ||
| popmean | No | ||
| sample1 | Yes | ||
| sample2 | No | ||
| alternative | No | two-sided |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that samples may be inline arrays or '@<path>' file references, a real behavioral trait beyond the schema, but it is silent on returned statistics, statistical assumptions, error behavior, and whether the file path must be readable. This is partial disclosure for a mutation-free compute tool.
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?
Two tight sentences, front-loaded with the core action, with the input-mode note as a secondary clause. There is no filler, though the file-reference detail could be integrated more compactly.
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 five-parameter statistical tool with no annotations and no output schema, the description covers the test variants and input modes but leaves parameter semantics for paired/popmean/alternative underexplained and says nothing about the returned test statistic or p-value. Adequate but with clear gaps.
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 0%, so the description must compensate. It explains the inline-or-file-reference semantics for sample inputs and hints at the alternative parameter ('one-sided alternative'), but paired and popmean are only obliquely implied by the test-mode names and get no semantic explanation. Partial compensation for a five-parameter tool.
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 states a specific verb (Run) and resource (t-test) and enumerates the three modes (one-sample, two-sample, paired) plus the alternative option. It is clear what the tool computes, though it does not name or contrast itself with siblings like chi2_test or anova that occupy adjacent statistical-testing territory.
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 the enumerated test variants and mentions an optional one-sided alternative, so the agent can infer which variant maps to its data shape, but it never states when to choose one-sample vs two-sample vs paired, nor when to prefer this over chi2_test or anova. Usage is implied rather than prescribed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.