psplot

Read-only

Plots propensity score distributions for treated and control groups to diagnose common support, with optional trimming lines.

Instructions

Propensity score distribution plot (common support diagnostic).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ax`	No	ax parameter.
`trim`	No	If set, draw vertical lines at (trim, 1-trim) to show the recommended trimming region.
`title`	No	title parameter (Optional[str]).
`treat`	Yes	Binary treatment column.
`colors`	No	Colors for (control, treated).
`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
`labels`	No	Labels for (control, treated).
`n_bins`	No	Number of histogram bins.
`figsize`	No	figsize parameter (tuple).
`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.
`covariates`	Yes	Covariates used to estimate the propensity score.
`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

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the read-only nature is covered. The description adds no additional behavioral context, such as that it estimates propensity scores from covariates and treatment, or that it returns a plot object. With annotations present, the bar is lower, but the description could have added useful context like the underlying estimation method.

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 a single, front-loaded sentence that states the core purpose without any fluff. It is appropriately sized and earns its place by conveying the primary intent clearly.

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 tool has an output schema and annotations cover safety, the description is minimally adequate. However, it does not explain the diagnostic's significance or how it relates to other propensity score tools, and it omits any mention of typical use cases (e.g., checking overlap before matching). For a tool with 15 parameters and many siblings, more context would help an agent decide when to invoke it.

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 parameters are documented in the schema. The description does not add any additional meaning to parameters. Per the baseline, when schema coverage is high, a score of 3 is appropriate; the description provides no extra value beyond the schema.

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 states the tool's function: 'Propensity score distribution plot (common support diagnostic).' It specifies the verb (plot), the resource (propensity score distribution), and the diagnostic purpose (common support). This distinguishes it from sibling plot tools like overlap_plot or love_plot by naming the specific diagnostic intent.

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 does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or alternative tools. The purpose 'common support diagnostic' implies usage for checking overlap, but no explicit guidance is provided. An agent would need to infer its applicability from the sibling names.

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

Deploy Server

Causal Decision Agent