Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

beyond_average_late

Read-only

Estimate the entire treatment-effect distribution among compliers under incomplete compliance using instrumental variables, providing quantile treatment effects beyond the average.

Instructions

Beyond-average LATE (Xie-Wu 2025). Identifies the entire treatment-effect distribution among compliers under incomplete compliance, not just its mean. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Selection-on-observables (unconfoundedness + overlap) or, for IV variants, instrument validity; For IV-QTE: rank invariance / rank similarity (monotonicity of the structural quantile function). Pre-conditions: Covariates, treatment, and outcome; for IV-quantile methods, a valid instrument; Enough data to estimate the outcome distribution across quantiles. Failure modes: Estimated conditional quantiles cross (non-monotone), or tail quantiles are unstable -> Use rearrangement / monotonization and avoid extreme quantiles where data are sparse. Alternatives: sp.qte, sp.iv, sp.dml. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`treat`	Yes	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
`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://.
`quantiles`	No	Quantiles tau at which to evaluate QTE (default 0.1..0.9 step 0.1)
`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.
`instrument`	Yes	instrument parameter (str).
`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

A4.6/5.0

Behavior5/5

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

The description discloses failure modes (quantile crossing, unstable tail quantiles), assumptions (unconfoundedness, instrument validity, rank invariance), pre-conditions, and a typical minimum N of 500. This goes well beyond the readOnlyHint annotation, which only signals no side effects. No contradiction with annotations.

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 well-structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, min N) and front-loads the purpose. However, the Validation sentence ('validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact)') is somewhat boilerplate and not directly actionable for invoking the tool, so it doesn't fully earn its place.

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?

For a complex econometric tool, the description covers the full decision surface: purpose, assumptions, pre-conditions, failure modes, alternatives, and data-size guidance. The output schema exists, so return-value details are secondary. Nothing an agent needs to select and invoke the tool correctly is missing.

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 has 100% description coverage, so the schema carries the burden. The description does not add parameter-level detail—it only lists generic pre-conditions (covariates, treatment, outcome, instrument) without mapping them to schema fields. The weak schema entry for 'instrument' (just 'instrument parameter (str).') is not compensated by the description.

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 opens with a clear verb+resource: 'Identifies the entire treatment-effect distribution among compliers under incomplete compliance, not just its mean.' It names the specific method (Xie-Wu 2025) and explicitly contrasts with the mean-based LATE, which distinguishes it from standard LATE tools and sibling quantile-treatment-effect tools.

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

Usage Guidelines5/5

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

The description ends with 'Alternatives: sp.qte, sp.iv, sp.dml', explicitly routing an agent to sibling tools. It also gives assumption-based selection guidance ('Selection-on-observables... or, for IV variants, instrument validity') and failure-mode remediation ('Use rearrangement / monotonization'), so an agent knows both when and when not to use this tool.

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

Deploy Server