Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rosenbaum_gamma

Read-only

Assess sensitivity of treatment effect estimates to hidden bias by computing Rosenbaum bounds for paired observational studies.

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

B3.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, covering the safety profile. The description adds the context that the tool applies to paired observational studies, which provides mild additional scope beyond the annotation. It does not contradict the read-only hint and no hidden side effects are relevant.

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?

The description is a single concise sentence with no wasted words and the core action is front-loaded. It is efficient, though very minimal; a bit more context could improve it without harming conciseness.

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?

Given the tool's high complexity (15 parameters, multiple input modes, many sibling sensitivity/bounds tools), the one-line description is insufficient. It does not explain how to supply data (e.g., data_path vs arrays), how to choose among methods, or how this tool relates to rosenbaum_bounds. The output schema and rich parameter descriptions partially compensate, but an agent would still struggle to decide when to invoke this tool.

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 input schema thoroughly documents all 15 parameters. The description itself adds no parameter-specific meaning, but the baseline of 3 is appropriate because the schema carries the full burden.

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 uses a specific verb ('Compute') and names a precise resource ('Rosenbaum bounds on a paired observational study'). It clearly indicates the tool's purpose but does not explicitly distinguish it from the sibling tool 'rosenbaum_bounds', which likely performs a related analysis.

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?

The description offers no guidance on when to use this tool versus alternatives such as 'rosenbaum_bounds' or 'sensitivity'. There is no mention of prerequisites, study design fit, or scenarios where this tool is preferable, leaving the agent to infer usage 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