Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

did_balance

Read-only

Audit DiD covariate balance: compute Imbens-Rubin normalized differences on levels and changes (weighted or not) and flag imbalances above 0.25 that threaten parallel trends.

Instructions

Covariate balance for a DiD design, in the shape Baker et al. (2026, Table 4) report it: Imbens-Rubin normalized differences computed twice -- once on baseline covariate LEVELS and once on covariate CHANGES across the treatment date -- optionally weighted and unweighted side by side. The changes panel is the informative half: DiD identifies off trends, so a covariate that is balanced in levels can still be moving differentially, and imbalances routinely flip sign between the two panels. Flags |norm. diff| > 0.25. Evidence about whether UNCONDITIONAL parallel trends is plausible; it cannot test parallel trends itself. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Known limitations: pooled multi-cohort balance is not implemented: one table per treated cohort only, because the normalized difference is a two-group statistic; only the reliability-weight variance correction is implemented for the weighted panel; survey-design (replicate-weight) variances are not supported; inference is not implemented: the normalized difference is reported as a descriptive effect size with no standard error or test, by design; the weighted denomi...

Input Schema

TableJSON Schema

Name	Required	Description	Default
`g`	Yes	First-treatment period (0 = never treated)
`i`	Yes	Unit identifier
`t`	Yes	t parameter (str).
`cohort`	No	Treated cohort to audit (default: the largest)
`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
`weights`	No	Unit weights; when given, weighted and unweighted statistics are reported side by side because they describe different populations
`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	Imbens & Rubin (2015, p. 277) rule of thumb
`covariates`	Yes	Columns to audit in levels and in changes
`base_period`	No	Pre-treatment period for the levels panel (default g-1)
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`control_group`	No	Must match the comparison group of the estimator you intend to run	nevertreated
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`comparison_period`	No	Second period for the changes panel (default g)

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

A4.4/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=true, openWorldHint=false), the description discloses extensive behavioral details: it computes normalized differences twice, flags |norm. diff| > 0.25, reports weighted and unweighted side by side, and lists limitations (pooled multi-cohort not implemented, only reliability-weight variance correction, no survey-design variances, no inference). 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 dense and front-loaded with the core purpose, but it is long and somewhat rambling (e.g., the truncated 'the weighted denomi...' and the validation tier aside). All sentences carry relevant information, but it could be more tightly structured. Not a tautology, but not as crisp as a two-sentence definition.

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?

Given the tool's complexity (16 parameters, output schema present), the description is exceptionally complete: it explains the method, the interpretation of the changes panel, the flagging rule, the evidence tier, and all major limitations. The output schema covers return structure, so the description does not need to detail return values. Very thorough.

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% and each parameter already has a detailed description (e.g., detail, weights, threshold, control_group). The tool description adds overall methodological context (why changes panel is informative) but does not add parameter-specific meaning beyond the schema, so 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 states a specific verb and resource: it computes Imbens-Rubin normalized differences for covariate balance in a DiD design, with levels and changes panels and optional weighting. This clearly distinguishes it from generic balance tools like love_plot or balance_diagnostics by tying it to DiD and the specific two-panel structure.

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 gives clear when-to-use context: it provides 'Evidence about whether UNCONDITIONAL parallel trends is plausible' and explicitly states it 'cannot test parallel trends itself,' implying a test tool is needed for that. However, it does not name specific sibling tools like did_test or parallel_trends_test, so the exclusion is implicit rather than explicitly routed.

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

Deploy Server