margins_at

Read-only

Compute predictive margins at specified covariate values to obtain adjusted predictions and contrasts from a fitted model. Provide a grid of variable values to get point estimates with confidence intervals.

Instructions

Compute predictive margins at specific covariate values. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`at`	Yes	Mapping of variable names to lists/arrays of values. If multiple variables are given, the Cartesian product of all value lists is used. Example:: at={"experience": [1, 5, 10], "female": [0, 1]} produces 6 grid points.
`alpha`	No	Significance level for confidence intervals.
`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
`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`	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.
`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

A3.5/5.0

Behavior3/5

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

The readOnlyHint annotation already covers the non-mutating nature, so the description does not need to repeat that. The first sentence is consistent with the annotation, and it adds the 'specific covariate values' scoping, but the validation-tier sentence is opaque and gives no concrete behavioral detail about runtime behavior, errors, or return semantics.

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 first sentence is front-loaded and precise, stating exactly what the tool does in a compact way. The second sentence about validation is cryptic and adds little actionable information, but the overall description remains short and not bloated.

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

Completeness4/5

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

Despite having nine parameters and a nested object, the schema provides full field descriptions and an output schema exists, so an agent can invoke the tool correctly without additional explanation. The main missing piece is a routing note for sibling margins tools, but that is a guidance gap rather than an invocation-blocking omission.

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 description need not restate parameter meanings. The phrase 'specific covariate values' loosely maps to the at parameter, but it adds no detail beyond the schema's already clear Cartesian-product explanation. Baseline of 3 is appropriate.

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 states the action ('Compute predictive margins') and the resource ('specific covariate values'), making the tool's purpose immediately understandable. However, it does not explicitly differentiate this tool from close siblings like margins, margins_at_plot, and margins_table, so it stops short of a top score.

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 phrase 'at specific covariate values' implies the intended use case, but the description provides no explicit when-to-use guidance, exclusion conditions, or alternatives. The 'Validation: validated evidence tier' sentence does not help an agent choose this tool over related margins tools.

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