Run the Augmented Dickey-Fuller test to determine whether a time series is stationary, reporting results at 5% significance.
Run the Augmented Dickey-Fuller test and report stationarity at 5%.
``regression`` is one of c, ct, ctt or n. ``autolag`` is AIC, BIC, t-stat
or None (no automatic lag selection).
| Name | Required | Description | Default |
|---|---|---|---|
| series | Yes | ||
| autolag | No | AIC | |
| regression | No | c |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does disclose a genuine behavioral constant (fixed 5% significance) and the autolag=None behavior, but says nothing about the return format, minimum sample requirements, or what a string-valued series means.
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 short, front-loaded sentences with zero filler; the core purpose comes first and the parameter value lists follow 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?
With no output schema and no annotations, the description should explain what is returned (p-value, test statistic, critical values) but only hints at a stationarity verdict. Combined with the undocumented required 'series' parameter, it is adequate but incomplete for a statistical test tool.
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, and it usefully enumerates valid values for regression (c, ct, ctt, n) and autolag (AIC, BIC, t-stat, None) that the schema does not encode. However, it completely omits the required 'series' parameter, which is ambiguous (array of numbers vs string), leaving the most important input undocumented.
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 verb ('Run') and resource ('Augmented Dickey-Fuller test') plus the output intent ('report stationarity at 5%'), so the agent knows exactly what computation happens. It is implicitly distinct from siblings like arima or time_series_decompose, but it never explicitly differentiates itself from them.
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?
There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as arima or time_series_decompose. The usage is only inferable from the test name itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.