Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

overlap_plot

Read-only

Plot mirrored density of propensity scores by treatment group to assess overlap and support causal analysis decisions.

Instructions

Mirrored density plot of propensity scores by treatment group.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ax`	No	Axes to plot on. If None, a new figure is created.
`ps`	No	Pre-estimated propensity scores.
`title`	No	Plot title.	Propensity Score Overlap
`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
`method`	No	PS estimation method if ps is None.	logit
`figsize`	No	Figure size (width, height).
`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	Binary treatment column.
`covariates`	Yes	Covariates for PS estimation (ignored if ps supplied).
`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

B3.4/5.0

Behavior3/5

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

The readOnlyHint annotation already communicates that this is a safe, non-mutating operation. The description adds that the output is a mirrored density plot, which is useful, but it does not disclose behavioral details such as the fact that propensity scores will be estimated when ps is omitted, or how results can be chained via as_handle.

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 a single, front-loaded phrase with no wasted words. It is concise and readable, though very sparse; it earns its place but could carry slightly more useful context without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the detailed schema, annotations, and output schema, the description is minimally adequate. However, it does not explain how this tool relates to similar sibling tools, what happens when ps is not supplied, or what the plot's practical use case is, so an agent must rely heavily on parameter descriptions and context signals.

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?

The input schema already describes all 13 parameters with 100% coverage, so the baseline is 3. The tool description adds no parameter-level meaning beyond referring generally to propensity scores and treatment group, which are already covered by the ps and treatment parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's output: a mirrored density plot of propensity scores by treatment group. It is more specific than the tool name and distinguishes this from generic plotting tools, though it does not name or differentiate against sibling tools like psplot or love_plot.

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?

Usage is implied: an agent can infer it should call this tool when it wants to visualize propensity score overlap across treatment groups. However, there is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives such as psplot or overlap_weights.

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

Deploy Server