Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

selection_bounds

Read-only

Compute Lee bounds for average treatment effect when outcomes are missing due to sample selection. Returns an interval estimate under weak assumptions, helping quantify causal effects with attrition.

Instructions

Lee (2009) bounds for ATE under sample selection, optionally Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Only weak (set-identifying) assumptions are imposed; the result is an interval, not a point; Lee bounds add monotonicity of selection; Oster's delta adds proportional selection on observed vs. unobserved. Pre-conditions: The data needed for the point-identifying analysis, plus the weakest credible identifying restriction; For Lee bounds: a binary selection/attrition indicator. Failure modes: Bounds are too wide to be informative -> Add a credible auxiliary restriction (monotone treatment response, instrument) to tighten the bounds. Alternatives: sp.oster_delta, sp.lee_bounds, sp.manski_bounds. Typical minimum N: 100.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable (may have NaN when selection=0).
`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
`method`	No	- ``'conditional'``: compute Lee bounds within covariate strata and average (tighter). - ``'unconditional'``: standard Lee bounds ignoring covariates.	conditional
`n_boot`	No	Number of bootstrap replications.
`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.
`selection`	Yes	Binary indicator: 1 = outcome observed, 0 = missing.
`treatment`	Yes	Binary treatment (0/1).
`covariates`	No	Covariates to condition on for tighter (conditional) bounds.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`random_state`	No	Random seed or RandomState for reproducible stochastic steps.
`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

A3.6/5.0

Behavior5/5

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

The description discloses several behavioral traits beyond annotations: the result is an interval, not a point; weak set-identifying assumptions; Lee bounds add monotonicity of selection; pre-conditions and failure modes are explicitly stated. This goes well beyond the readOnly/openWorld hints.

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 description packs a lot of information (assumptions, pre-conditions, failure modes, alternatives, typical N) but is not well structured and the opening sentence mixes two clauses ('Lee (2009) bounds... optionally Validation:'). It could be shorter and better organized.

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

Completeness4/5

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

Given the tool's complexity (14 params, output schema), the description covers assumptions, pre-conditions, failure modes, and typical sample size. It does not explain return values, but an output schema exists. Minor gaps: no explicit link between the 'method' parameter and the described tightening behavior, and alternatives are not differentiated. Overall, sufficient for an agent to call the tool correctly.

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 already documents all 14 parameters. The description reinforces the binary selection indicator and mentions conditional vs unconditional method, but adds no new parameter-level detail beyond what the schema provides.

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?

States a specific verb+resource: computes Lee (2009) bounds for ATE under sample selection. However, it lists sibling tools sp.lee_bounds, sp.oster_delta, sp.manski_bounds as alternatives without explaining how this tool differs from them, so it doesn't fully disambiguate.

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?

Lists alternatives but provides no conditions for choosing among them. No explicit when-to-use or when-not-to-use guidance. The failure mode mentions adding restrictions to tighten bounds, but that's about method choices, not tool selection.

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

Deploy Server