Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

margins_table

Read-only

Compute marginal effects from a fitted model and format them into a regression table for direct reporting and further analysis.

Instructions

Marginal-effects result that pipes straight into sp.regtable.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`at`	No	Forwarded verbatim to :func:`margins`.
`eps`	No	Forwarded verbatim to :func:`margins`.
`alpha`	No	Forwarded verbatim to :func:`margins`.
`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	Forwarded verbatim to :func:`margins`.	ame
`result`	Yes	Fitted model -- same input ``sp.margins`` accepts.
`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	Forwarded verbatim to :func:`margins`.
`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

C2.5/5.0

Behavior2/5

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

The readOnlyHint annotation already covers the read-only nature. The description adds only that the result is formatted for regtable, but does not disclose behaviors like caching (as_handle), subsampling (data_sample_n), or how the result is piped.

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?

A single terse sentence with no filler. The key phrase 'pipes straight into sp.regtable' is front-loaded and communicates the primary integration point efficiently.

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

Completeness2/5

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

With 12 parameters including complex ones like data_path and as_handle, and an output schema available, the description is far too minimal. It does not explain that the tool computes marginal effects on a fitted model, nor how it relates to the sibling margins tool, leaving an agent under-informed.

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 coverage is 100%, so the schema carries the full parameter descriptions. The tool description adds no parameter-level meaning, so the baseline of 3 is appropriate.

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

Purpose3/5

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

The description identifies the tool's output as a marginal-effects result intended for sp.regtable, which gives a rough sense of purpose. However, it lacks a clear verb and does not distinguish it from the many margin-related siblings (e.g., margins, margins_at, marginsplot).

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

Usage Guidelines1/5

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

No guidance is given on when to use this tool versus the numerous margin-related alternatives. No when-not-to-use, prerequisites, or selection criteria are mentioned.

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

Deploy Server