Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

pcmci

Read-only

Reveal causal structure in stationary time-series data, estimating lagged dependencies and testing conditional independence to separate direct causes from spurious correlations.

Instructions

PCMCI causal discovery for stationary time-series. 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

Name	Required	Description	Default
`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
`ci_test`	No	Custom CI test ``(x, y, Z) -> p_value``. Defaults to :func:`partial_corr_pvalue`.
`tau_max`	No	Maximum lag to consider for parent candidates.
`verbose`	No	verbose parameter (bool).
`pc_alpha`	No	Significance threshold used during the PC1 selection stage.
`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://.
`mci_alpha`	No	Significance threshold for the final MCI adjacency. Defaults to ``pc_alpha``.
`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.
`variables`	No	Columns to use. Defaults to all columns.
`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.
`max_conds_dim`	No	Hard cap on the conditioning-set size during PC1. ``None`` means no cap (the algorithm stops automatically when no predictors remain).

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

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description doesn't need to repeat that. It adds rich behavioral context: assumptions (Causal Markov, faithfulness, acyclicity), failure modes (unstable skeleton, likely culprits), and typical minimum N. This goes well beyond the 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 organized into labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) which makes it scannable. It is somewhat long but every sentence carries useful information—no fluff.

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 tool, this description covers assumptions, preconditions, failure modes, alternatives, and sample size guidance. An output schema exists, so return format is already documented. Nothing an agent needs to decide when and how to call this tool is missing.

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 all 13 parameters are documented. The description adds some meaning by linking failure modes to parameter choices (e.g., 'relax the CI-test threshold'), but it doesn't explain specific parameters beyond what the schema already provides. 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?

States a specific verb+resource ('PCMCI causal discovery for stationary time-series') and names alternatives (sp.pc_algorithm, sp.fci, sp.ges, sp.lingam), clearly distinguishing it from siblings like pc_algorithm, fci, ges, lingam in the sibling list.

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 pre-conditions (i.i.d. data for constraint/score-based, labelled environments for invariance-based) and names alternatives explicitly. Also gives failure modes and typical minimum N, giving clear guidance on when to use and when not.

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

Deploy Server