Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

fci

Read-only

Learn a causal graph (PAG) from observational data while allowing latent confounders, using conditional independence tests to reveal direct and indirect causal links.

Instructions

Run FCI. Returns a :class:FCIResult with the learned PAG. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Causal Markov condition and faithfulness (PC/GES/FCI); Causal sufficiency for PC/GES (no latent confounders); FCI relaxes this; Acyclicity; LiNGAM additionally assumes a linear non-Gaussian model. Pre-conditions: Constraint-/score-based discovery needs i.i.d. observational data with enough samples for reliable conditional-independence tests; Invariance-based discovery (ICP) needs data labelled by environment / intervention. Failure modes: Unstable skeleton / many undirected edges -- faithfulness or sample size is the likely culprit -> Increase the sample, relax the CI-test threshold, or switch to FCI if latent confounders are plausible. Alternatives: sp.pc_algorithm, sp.fci, sp.ges, sp.lingam. Typical minimum N: 500.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
alphaNoSignificance level for CI 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
ci_testNoOnly Fisher-Z partial-correlation test is supported; extensions (kernel / chi-square) can be added later.fisherz
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.
variablesNoColumns to use; defaults to all numeric 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.
max_cond_sizeNoMax size of conditioning set.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations (readOnlyHint=true, openWorldHint=false) already signal read-only, closed-world behavior. The description adds substantial behavioral context: return type (FCIResult), validation tiers, assumptions, failure modes with mitigation strategies, and minimum sample size. No contradiction with annotations; 'Run FCI' is consistent with read-only computation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is organized with clear labels (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) and front-loads the core purpose. Each sentence adds distinct value; no fluff. Despite length, it is dense and well-structured.

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?

For a complex causal discovery algorithm with 10 parameters and an output schema, the description covers return type, assumptions, pre-conditions, failure modes, alternatives, and sample size guidance. The output schema handles return details, so nothing essential is missing. Very complete.

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 parameters like alpha, ci_test, and data_path are already documented. The description does not add specific parameter meaning beyond the schema; it only indirectly references alpha via 'relax the CI-test threshold.' Baseline 3 is appropriate because schema carries the load.

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 clearly states 'Run FCI' and specifies the output as a `FCIResult` with the learned PAG. It distinguishes FCI from siblings by naming alternatives (sp.pc_algorithm, sp.ges, sp.lingam) and explaining when FCI is preferred (latent confounders). This is specific and non-tautological.

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

Usage Guidelines5/5

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

Provides explicit when-to-use guidance: assumptions contrast FCI with PC/GES (FCI relaxes causal sufficiency), and failure modes explicitly say 'switch to FCI if latent confounders are plausible.' Also covers pre-conditions (i.i.d. data, enough samples, environment labels for ICP) and typical minimum N=500. This is thorough routing.

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