Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

compare_estimators

Read-only

Compare causal effect estimates from multiple estimators on the same data to evaluate robustness and select a reliable method.

Instructions

Run multiple estimators on the same data and compare.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yYesOutcome variable.
idNoPanel unit ID.
timeNoTime variable.
alphaNoSignificance level for confidence intervals and tests.
detailNoPayload 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
methodsNoEstimators to compare. Default auto-selects based on data. Classical options: ``'ols'``, ``'matching'``, ``'ipw'``, ``'aipw'``, ``'dml'``, ``'g_computation'``, ``'causal_forest'``, ``'did'``, ``'panel_fe'``. Hint-driven Sprint-B options (require ``method_hints``): ``'proximal'``, ``'msm'``, ``'principal_strat'``, ``'mediate'``, ``'mediate_interventional'``, ``'front_door'``. Each needs method-specific kwargs the shared signature does not expose (proxy_z/proxy_w, time_varying, strata, mediator, etc.) -- pass them through ``method_hints``.
as_handleNoIf 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_pathYesAbsolute 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_idNoOptional 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.
treatmentYesTreatment variable (binary).
covariatesNoCovariate matrix, DataFrame, or column names.
instrumentNoinstrument parameter (Optional[str]).
data_columnsNoOptional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
method_hintsNoPer-method keyword overrides, merged with the shared kwargs when dispatching each estimator. Structure:: {'proximal': {'proxy_z': ['z'], 'proxy_w': ['w']}, 'msm': {'time_varying': ['L_lag']}, 'principal_strat': {'strata': 's'}} **Collision rule** (docs/ROADMAP.md Section 6): per-method hints take precedence over the shared kwargs for the method they name. If the top-level ``covariates=['age']`` disagrees with ``method_hints={'proximal': {'covariates': ['age', 'educ']}}``, proximal uses the hint and every other method uses the shared arg. A ``UserWarning`` fires on conflict so the override is visible in the log.
data_sample_nNoOptional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

With readOnlyHint=true, the annotation already tells the agent this is a safe read/compute operation. The description adds no behavioral detail beyond the name's implication, such as caching via as_handle, method auto-selection, or the fact that hints control advanced estimators. Since it adds no context beyond the annotation, a low score is warranted.

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 single-sentence description is extremely concise and front-loaded, with no filler. For a 15-parameter tool, however, it is almost too terse; the schema must do all the explanatory work. It earns a high but not top score.

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 tool has a rich schema, an output schema, and a readOnlyHint, so the description does not need to explain return values or side effects. Still, it omits high-level context about auto-selected methods, the comparison output structure, and when this tool is the right choice among many siblings. The one-line description plus schema is minimally viable but not complete for an agent facing a large toolbox.

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 baseline is 3. The description itself mentions 'same data' and 'multiple estimators', which loosely maps to data_path and methods, but adds no parameter details beyond the schema. The rich per-parameter descriptions carry the semantic load.

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?

Description uses a clear verb ('Run') and object ('multiple estimators') and states the purpose 'compare'. It is unambiguous about the core function. However, it does not differentiate from siblings like compare_metalearners or panel_compare, which also involve running and comparing estimators, so it stops short of 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 Guidelines2/5

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

The description gives no indication of when to prefer this tool over alternatives such as compare_metalearners or panel_compare. There are no exclusion criteria, no mention of the auto-selection of methods, and no guidance on prerequisites. An agent must infer usage from the parameter schema.

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

Deploy Server

Other Tools