wild_cluster_ci_inv

Read-only

Inverts wild bootstrap p-values to compute cluster-robust confidence intervals, providing validated evidence tiers for causal analysis.

Instructions

Confidence interval via bootstrap p-value inversion. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	Outcome variable column name or outcome array.
`seed`	No	Random seed for reproducible stochastic steps.
`alpha`	No	Significance level for confidence intervals and tests.
`detail`	No	Payload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip.	agent
`n_boot`	No	Number of bootstrap replications.
`cluster`	Yes	Cluster identifier column for clustered standard errors.
`test_var`	No	test_var parameter (Optional[str]).
`as_handle`	No	If true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running.
`data_path`	Yes	Absolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://.
`grid_size`	No	Number of null-value grid points to evaluate (odd preferred).
`grid_span`	No	Half-width of the search grid in units of cluster-robust SE.
`result_id`	No	Optional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns.
`weight_type`	No	weight_type parameter (str).	webb
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already provide readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds the validation-tier disclosure, which is useful context about the output's evidence quality. However, it doesn't mention potential computational intensity or other behavioral traits; the added sentence is the only extra.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with no redundancy, and the core purpose is front-loaded. Every word adds value, making it a model of concise, structured description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 16 parameters, 4 required, many similar siblings, and an output schema present, the description is too thin. It doesn't explain what kind of model/data this applies to, how it relates to other wild cluster tools, or when to choose it. An agent must infer all this from the name and schema, which is a heavy lift.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are already well-documented. The description adds no parameter-level semantics beyond what the schema provides. The baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific operation: computing a confidence interval via bootstrap p-value inversion. This is a clear verb and resource, and it differentiates from simple bootstrap p-value tools like wild_cluster_boot. However, it does not explicitly name sibling alternatives or clarify the cluster/data context beyond the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. The description does not state when to prefer this tool over wild_cluster_boot or wild_cluster_bootstrap, nor does it mention prerequisites such as clustered data or model type. An agent must infer applicability from the name and schema.

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

Deploy Server

Causal Decision Agent