Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

pwcompare

Read-only

Compare predictive margins across all levels of a categorical variable to identify which pairs differ significantly, with optional multiple-comparison adjustments for evidence-backed decisions.

Instructions

Pairwise comparisons of predictive margins across all levels. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`alpha`	No	Significance level for (adjusted) confidence intervals.
`adjust`	No	P-value adjustment method: - ``'none'``: unadjusted. - ``'bonferroni'``: Bonferroni correction. - ``'sidak'``: Sidak correction. - ``'holm'``: Holm step-down procedure.	none
`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
`result`	Yes	Fitted model result.
`variable`	Yes	Categorical variable whose levels are compared pairwise.
`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://.
`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.
`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

C2.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The phrase 'across all levels' adds a useful scoping constraint that all levels are compared, not a custom subset. The validation note is more of a provenance tag than an operational behavior, but nothing contradicts the annotations.

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

Conciseness3/5

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

The purpose sentence is concise and front-loaded, which is good. However, the second sentence about validation evidence tier does not help an agent select or invoke the tool correctly, so not every sentence earns its place.

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 10 parameters and a very large sibling-tool set, the two-line description offers little workflow context, such as how the fitted result should be produced or how detail/as_handle interact in a multi-step pipeline. The rich schema and output schema prevent this from being a complete failure, but the description alone is still not adequate for confident tool selection.

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?

The input schema fully documents all 10 parameters, so the schema carries most of the semantic burden. The description adds only the 'across all levels' nuance, which reinforces but does not significantly extend the variable parameter's existing pairwise-comparison description.

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 first sentence identifies the operation precisely: pairwise comparisons of predictive margins across all levels. This is specific enough to be distinguished from generic margins or contrast tools at a glance, though it does not explicitly name any sibling or state what kind of fitted result it requires.

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 guidance is provided about when to use pwcompare rather than alternatives such as contrast, lincom, or margins. The validation sentence adds provenance information but no decision context, so the intended usage must be inferred from the tool name and one-line purpose.

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

Deploy Server