Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

ebalance

Read-only

Balance covariate means across treatment groups to estimate the average treatment effect on the treated (ATT) without propensity-score models, yielding certified parity evidence.

Instructions

Hainmueller (2012) entropy balancing. Targets the ATT by exactly balancing covariate means across treatment groups. No propensity-score model specification needed. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes
`treat`	Yes
`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
`moments`	No	Max moment balanced (1=means, 2=vars).
`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.
`covariates`	Yes
`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

B3.4/5.0

Behavior3/5

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

Annotations already provide readOnlyHint=true, and the description adds the methodological note that no propensity-score model is needed. However, it does not describe what the output contains or how the validation evidence is produced, leaving some behavioral aspects under-specified.

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 two sentences and front-loads the core purpose efficiently. The final fragment 'Validation: certified parity evidence' is cryptic and may not earn its place for an agent, but overall the text is tight and to the point.

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?

Given the complexity of entropy balancing, the description is somewhat light. It doesn't explain when to choose this over cbps or sbw, nor what the validation output implies. With an output schema present, the return format is covered, but the strategic context for selecting this tool is incomplete.

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 70%, so most parameters like covariates, treat, y, detail, and as_handle already have explanatory descriptions. The tool description itself does not add meaning beyond mentioning 'covariate means', which is generic. At 70% coverage, baseline of 3 is appropriate.

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 clearly identifies the tool as Hainmueller (2012) entropy balancing, specifies the target estimand (ATT), and describes the balancing mechanism (exactly balancing covariate means). This is specific and differentiates it from propensity-score-based approaches, though it does not name sibling tools.

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

Usage Guidelines3/5

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

The description implies usage when the user wants ATT without specifying a propensity-score model, but it provides no explicit 'when to use vs alternatives' or exclusions. The lack of sibling mentions or criteria leaves the agent to infer the appropriate context.

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

Deploy Server