Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

vcnet

Read-only

Estimates a smooth causal dose-response curve from observational data with continuous treatment, covariates, and outcome. Returns confidence intervals and diagnostics.

Instructions

Varying-coefficient dose-response estimator. Assumptions: Unconfoundedness given covariates X (no hidden confounding of the continuous treatment); Positivity over the dose: every dose has support across X; The dose-response curve is smooth (varying-coefficient prior). Pre-conditions: data with a continuous treatment (dose), outcome and covariates; torch is installed (neural extra) -- imported lazily. Failure modes: Sparse support at extreme doses yields an unreliable dose-response curve there -> Restrict the reported dose range to the supported region or compare against scigan. Alternatives: sp.scigan, sp.dose_response. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`alpha`	No	Significance level for confidence intervals and tests.
`ridge`	No	Tikhonov regularisation on the coefficient matrix.
`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
`t_grid`	No	Treatment values at which to evaluate the dose-response curve. Defaults to 40 equally-spaced points between the observed min/max.
`n_basis`	No	Number of B-spline basis functions for the t-axis.
`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://.
`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	Continuous treatment / dose column.
`covariates`	Yes	Covariate matrix, DataFrame, or column names.
`n_bootstrap`	No	Number of bootstrap replications.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`random_state`	No	Random seed or RandomState for reproducible stochastic steps.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`spline_degree`	No	spline_degree parameter (int).

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

A4.7/5.0

Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description adds rich behavioral context: assumptions (unconfoundedness, positivity, smoothness), lazy torch import, unreliability at sparse extreme doses, and typical minimum N. It discloses when results may be untrustworthy and how to mitigate, which is valuable for an agent deciding whether to trust the output.

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 compact and dense, with every sentence providing useful operational or inferential guidance. It front-loads the estimator's purpose, then assumptions, preconditions, failure modes, and alternatives in a logical order. No filler or repetition.

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 estimator with nuanced assumptions, the description covers purpose, assumptions, preconditions, failure modes, alternatives, and sample size guidance. An output schema exists so return-value documentation is not required here. The description is complete for an agent to decide when to invoke this tool and how to interpret its limitations.

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 parameters are fully documented in the input schema. The description itself does not elaborate on any parameter semantics, but it does not need to given the schema completeness. Baseline 3 is appropriate since the schema carries the heavy lifting.

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 identifies the tool as a varying-coefficient dose-response estimator with a specific resource (dose-response curve). It distinguishes itself from siblings by naming alternatives (sp.scigan, sp.dose_response) and describing the estimand. The phrase is a noun, but it unambiguously states what the tool computes and the assumptions required.

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 pre-conditions (continuous treatment, outcome, covariates, torch installed), failure modes, and a recommended action in failure (restrict dose range or compare against scigan). It also names alternatives, giving an agent clear routing guidance between this and sibling tools.

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

Deploy Server