Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

llm_sensitivity_priors

Read-only

Propose sensitivity-analysis priors for causal inference from domain context and candidate variables, delivering hypotheses that need validation before causal claims.

Instructions

Propose sensitivity-analysis priors for the substantive setting. Assumptions: LLM-proposed graphs / priors are hypotheses to validate, not statistical identification; Human review or data-driven falsification is required before any causal claim. Pre-conditions: Domain context and a bounded list of candidate variables; A configured, logged LLM provider for reproducibility. Failure modes: Proposals are unstable across runs or include hallucinated variables/edges -> Fix the model release and seed, add constraints, and cross-check with constraint-based discovery. Alternatives: sp.llm_dag_constrained, sp.causal_discovery, sp.dag. Typical minimum N: 1.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`client`	No	LLM client with ``.complete(prompt: str) -> str``.
`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
`domain`	No	domain parameter (str).	health
`outcome`	Yes	Outcome variable column name or outcome array.
`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`	No	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://.
`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.
`treatment`	Yes	Treatment indicator, treatment variable, or treatment array.
`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.

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 only provide readOnlyHint=true and openWorldHint=false, but the description adds rich behavioral context: failure modes ('Proposals are unstable across runs or include hallucinated variables/edges'), the requirement for validation ('Human review or data-driven falsification is required before any causal claim'), and assumptions about statistical identification. This goes well beyond the annotations without contradicting them.

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 with clear sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) and is front-loaded with the purpose. While it is longer than average, every section contributes necessary guidance, so it earns a 4 rather than 5 for slight verbosity relative to the tool's simplicity.

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?

The description covers assumptions, preconditions, failure modes, alternatives, and a typical minimum N. With an output schema present, it need not explain return values. It provides all essential context for an agent to correctly invoke and interpret the tool, making it 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 the schema already explains each parameter. The description mentions preconditions like 'Domain context' and 'bounded list of candidate variables' but does not explicitly map these to specific parameters (e.g., outcome, treatment, domain). It adds minimal semantic value beyond the schema, so a 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?

The description opens with 'Propose sensitivity-analysis priors for the substantive setting,' stating a specific verb (propose) and resource (sensitivity-analysis priors). It clearly differentiates itself from siblings by naming alternatives like sp.llm_dag_constrained, sp.causal_discovery, and sp.dag, so an agent can distinguish it without inspecting schemas.

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?

The description explicitly lists 'Alternatives' and provides precondition requirements ('Domain context and a bounded list of candidate variables; A configured, logged LLM provider for reproducibility'). It also clarifies the epistemological stance ('hypotheses to validate, not statistical identification') and the need for human/data-driven falsification, giving clear when-to-use and when-not-to-use guidance.

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

Deploy Server