Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

dag

Read-only

Declare a causal graph and run identification analysis: compute adjustment sets, test d-separation, enumerate paths, detect bad controls, and classify variable roles.

Instructions

Declare a causal DAG and perform identification analysis: backdoor/frontdoor adjustment sets, d-separation, path enumeration, bad controls detection, variable role classification, do-operator. Assumptions: The graph is acyclic and contains the relevant common causes; Adjustment-set validity depends on the supplied graph being substantively correct. Pre-conditions: Nodes and directed edges encode a substantive causal model; Treatment and outcome nodes are named consistently. Failure modes: No valid adjustment set or cycle detected -> Inspect graph structure, remove cycles, or use sensitivity analysis for unobserved common causes. Alternatives: sp.identify, sp.dag_recommend_estimator, sp.swig. Typical minimum N: 1.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
specYesEdge spec: "Z -> X; Z -> Y; X -> Y"
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
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.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already mark this readOnlyHint=true, and the description adds substantial behavioral context beyond that: acyclicity assumptions, dependence on substantive correctness of the graph, preconditions about node encoding, and concrete failure modes with remediation steps. It does not contradict 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 purpose is front-loaded and each section (assumptions, preconditions, failure modes, alternatives) earns its place. It is somewhat dense, but the structure makes it scannable and the brevity is appropriate for a tool with many capabilities.

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 DAG-identification tool, the description covers the key contextual needs: when assumptions fail, what preconditions must hold, what to do on failure, and where to look for alternatives. The output schema handles return-value expectations, so nothing essential is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the parameter descriptions are already detailed (edge spec syntax, detail payload depths, caching behavior). The description adds extra semantic guidance on what the graph content should encode: treatment/outcome node naming consistency and availability of relevant common causes, which helps an agent form a correct spec.

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 names a specific verb ('Declare') and a specific resource ('a causal DAG'), then enumerates concrete capabilities: backdoor/frontdoor adjustment sets, d-separation, path enumeration, bad controls detection, variable role classification, and do-operator. This is far more specific than the tool name 'dag' alone and distinguishes it from generic causal tools.

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

Usage Guidelines3/5

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

The description includes explicit alternatives (sp.identify, sp.dag_recommend_estimator, sp.swig) and a failure-mode hint to use sensitivity analysis for unobserved common causes, which is useful guidance. However, it never states when to prefer this tool over those alternatives or when not to use it, so the agent must infer the routing from context.

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