Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

lee_bounds

Read-only

Compute Lee (2009) bounds for the average treatment effect when outcomes are missing for some units. Returns an interval that accounts for sample selection, enabling causal inference under weak assumptions.

Instructions

Compute Lee (2009) bounds for ATE under sample selection. 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 for selected-out units).
`alpha`	No	Significance level.
`treat`	Yes	Binary treatment variable (0/1).
`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
`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 selection/retention indicator (1 = observed, 0 = missing).
`covariates`	No	Not used in basic Lee bounds, reserved for conditional bounds.
`n_bootstrap`	No	Bootstrap iterations for inference.
`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

A4/5.0

Behavior3/5

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

Annotations only declare readOnlyHint=true, so the description covers the rest. It states the tool imposes weak assumptions, returns an interval, and adds monotonicity of selection. However, it doesn't disclose details like bootstrap defaults, output structure, or the effect of alpha parameter. It doesn't contradict readOnlyHint.

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 fairly dense with useful info (validation, assumptions, failure modes, alternatives, min N), but it's a bit long and could be front-loaded with the tool's purpose more clearly. No fluff, but some reorganization would improve scannability.

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

Completeness5/5

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

The description covers assumptions, pre-conditions, failure modes, alternatives, and minimum N. Combined with the output schema and full parameter documentation, an agent has enough to call this correctly. The description adds value beyond structured fields by explaining the interval nature and selection requirement.

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 coverage is 100%, so parameters are already well documented. The description adds context for 'selection' (binary selection/attrition indicator) and mentions covariates are reserved for conditional bounds, but doesn't add syntax beyond the schema. Baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states the tool computes Lee (2009) bounds for ATE under sample selection and explains it returns an interval, not a point estimate. It distinguishes from related bounds tools by name (oster_delta, lee_bounds, manski_bounds).

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

Usage Guidelines4/5

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

The description provides alternatives (oster_delta, lee_bounds, manski_bounds) and failure modes (bounds too wide -> add auxiliary restriction). However, it doesn't explicitly state when to use Lee bounds vs. these alternatives, nor when not to use it, though the assumptions section implies context.

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

Deploy Server