Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

margins

Read-only

Calculate marginal effects from a fitted model to quantify each predictor's impact on the outcome, with options for average marginal effects or conditional at values.

Instructions

Compute marginal effects from a fitted model. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`at`	No	Fix covariates at specific values for conditional margins. E.g., ``{'age': 30, 'female': 1}``.
`eps`	No	Step size for numerical differentiation.
`alpha`	No	Significance level.
`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	- 'ame': Average Marginal Effect (average dy/dx across all obs) - 'mem': Marginal Effect at the Mean (dy/dx at mean of X)	ame
`result`	Yes	Fitted model result (must have ``.params`` and associated data).
`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.
`variables`	No	Variables to compute dy/dx for. Default: all regressors.
`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

B3.1/5.0

Behavior3/5

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

The readOnlyHint annotation already establishes that this is a non-mutating operation, lowering the burden on the description. The added 'validated evidence tier' note is a non-operational form of context, but the description does not go into concrete behavior such as caching, result identity, or when as_handle matters. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is clear and front-loaded, but the second sentence about 'validated evidence tier' is cryptic and does not clearly earn its place. The definition is short, but one of its two sentences adds little actionable value.

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?

The rich input schema and presence of an output schema compensate for much of what the description omits. However, for a tool in a very large sibling family, the description provides no positioning or high-level guidance, leaving the agent to infer context from the schema alone.

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 already well documented. The description itself adds no parameter-level meaning beyond the general 'fitted model' context, which matches the baseline for full schema coverage.

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 names a specific verb and resource: 'Compute marginal effects from a fitted model.' This is clear and unambiguous, but it does not differentiate from closely related siblings such as margins_at, margins_table, or marginsplot, so it stops short of a 5.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives like margins_at or margins_table, nor any mention of prerequisites beyond 'fitted model.' The schema covers mechanics, but the description offers no decision-making context.

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

Deploy Server