Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

balance_diagnostics

Read-only

Check covariate balance after matching or weighting, estimate propensity scores if needed, and get violation flags plus next steps for causal analysis.

Instructions

Unified balance diagnostics for matching and weighting estimators.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ps`	No	Propensity scores. If omitted, estimated with ``method``.
`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	Propensity-score model when ``ps`` is not supplied.	logit
`weights`	No	Observation weights after matching/weighting. If omitted, ATE inverse-propensity weights are computed from ``ps``.
`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.
`threshold`	No	Balance threshold for absolute standardized mean differences.
`treatment`	Yes	Binary treatment indicator.
`covariates`	Yes	Covariates to audit.
`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?

The readOnlyHint annotation already covers the read-only safety profile, lowering the burden on the description. The description adds the estimator scope ('matching and weighting estimators') but does not disclose behavioral details such as what diagnostics are included, whether it is a composite call, or any side effects beyond the annotation.

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 that names the tool's domain without filler. It is not verbose, though it may be too terse to fully orient an agent among the many sibling balance-related tools.

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?

The rich input schema and output schema carry substantial explanatory weight, and annotations confirm read-only behavior. However, for a tool with 12 parameters and many related siblings, the one-line description does not fully contextualize when this 'unified' diagnostic should be invoked versus alternatives like ps_balance or balance_panel.

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 already documents all 12 parameters in detail, including the meaning of 'weights', 'ps', 'method', and 'detail'. The description itself adds no parameter-level meaning beyond mapping the tool to matching/weighting contexts, so the baseline score 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 identifies the tool as providing 'balance diagnostics' for 'matching and weighting estimators', which clearly indicates its subject area. It lacks an explicit verb and does not differentiate itself from sibling tools like balance_panel, ps_balance, or balanceplot, so it cannot earn a 5.

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 phrase 'for matching and weighting estimators' gives an implied usage context: call this after matching or weighting-based estimation to check balance. However, there is no explicit guidance about when to choose this tool over sibling diagnostics, nor any when-not-to-use exclusions.

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

Deploy Server