Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rosenbaum_bounds

Read-only

Test whether a paired observational study's treatment effect is robust to unmeasured confounding by computing Rosenbaum bounds and gamma-critical values.

Instructions

Compute Rosenbaum bounds on a paired observational study.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	No	Outcome variable column name or outcome array.
`alpha`	No	Significance level used to report ``gamma_critical``.
`treat`	No	Treatment indicator or first-treatment-period column.
`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
`method`	No	Wilcoxon signed-rank bound (continuous) or binomial sign test (robust / binary).	wilcoxon
`control`	No	Outcome in the treated / control unit of each matched pair (same length). Ignored if ``data`` is provided.
`pair_id`	No	pair_id parameter (Optional[str]).
`treated`	No	Outcome in the treated / control unit of each matched pair (same length). Ignored if ``data`` is provided.
`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`	No	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.
`gamma_grid`	No	Gamma values (>= 1) over which to compute bounding p-values.
`alternative`	No	Direction of the alternative hypothesis for the treatment effect.	greater
`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

Behavior2/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data. The description adds no behavioral context beyond the word 'Compute' — it does not clarify the input-output flow, that it returns bounding p-values over a gamma grid, or any interpretation caveats. It is consistent with annotations (no contradiction) but contributes little.

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

Conciseness4/5

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

A single efficient sentence that names the operation and study context without waste. It is slightly under-specified for the complexity of the tool, but as a compact statement it is well-structured.

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

Completeness3/5

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

An output schema exists and parameter coverage is 100%, so the structured fields carry much of the burden. However, for a 15-parameter tool the description is thin — it omits when to apply this technique, what the result represents, and how it relates to rosenbaum_gamma, leaving the agent to rely entirely on parameter names.

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 the schema fully documents all 15 parameters including enums, defaults, and the detail-level payload guidance. The description adds no parameter meaning beyond the schema, matching the baseline of 3 for high coverage.

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?

Description states a clear verb ('Compute'), resource ('Rosenbaum bounds'), and context ('paired observational study'). It is specific enough to convey the core function, but it does not distinguish itself from closely related siblings such as rosenbaum_gamma or sensitivity, which appear in the sibling list and overlap in purpose.

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 on when to use this tool versus alternatives. It does not mention when Rosenbaum bounds are appropriate (e.g., sensitivity to hidden bias in matched pairs) nor exclude scenarios better handled by rosenbaum_gamma, sensitivity, or selection_bounds. The agent must infer applicability from the name alone.

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

Deploy Server