Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

absorb_ols

Read-only

Run OLS with absorbed high-dimensional fixed effects to control for unobserved group heterogeneity. Obtain cluster-robust standard errors and diagnostics for causal decision-making.

Instructions

OLS with absorbed high-dimensional fixed effects (reghdfe-style).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
XYesRegressors *excluding* the absorbed FEs and the constant (the constant is absorbed by any FE dimension).
yYesOutcome variable column name or outcome array.
feYesFixed-effect columns.
tolNoDemean convergence controls.
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
slopesNoslopes parameter (Optional[Sequence[SlopeSpec]]).
solverNoWithin-transformation backend. See :class:`Absorber`.map
clusterNoOne-way or multi-way cluster variables for robust SEs. If provided, returns cluster-robust SEs (one-way: Liang-Zeger sandwich; multi-way: inclusion-exclusion Cameron-Gelbach-Miller).
maxiterNoDemean convergence controls.
weightsNoObservation weights.
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_pathNoAbsolute 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.
data_columnsNoOptional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
data_sample_nNoOptional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
drop_singletonsNodrop_singletons parameter (bool).
return_absorberNoIf True, also return the ``Absorber`` object for reuse.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description does not contradict them. The reghdfe-style reference adds minimal algorithmic identity (within-transformation/demeaning), but the description itself discloses little beyond what the annotations and schema already carry.

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?

Eight words with zero padding, and the core method is front-loaded in the first clause. It is efficient, though it leaves spare capacity that could have held a one-line usage hint without bloat.

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 output schema and exhaustive parameter documentation cover return values and arguments, so those gaps are closed. The main missing piece is selection context among the roughly 70 siblings, which matters for a complex 17-parameter estimation tool.

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% and the schema is exceptionally rich, covering token budgets for detail, SE formulas for cluster, solver backends, and chaining via as_handle/result_id. The description contributes no parameter-level meaning, so the schema-carrying baseline of 3 applies.

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 states a specific verb and resource: OLS with absorbed high-dimensional fixed effects, anchored by the well-known 'reghdfe-style' reference. It is clear what the tool computes, but it does not explicitly differentiate itself from close siblings like hdfe_ols, feols, or demean.

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?

No guidance is given on when to use absorb_ols versus alternatives such as regress, hdfe_ols, feols, feglm, fepois, or ppmlhdfe. There are no exclusions, preconditions, or context cues beyond the name itself, leaving tool selection to inference.

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