Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

evalue_from_result

Read-only

Compute the E-value from a fitted causal result to quantify how strongly unmeasured confounding must be to explain away the observed effect.

Instructions

Compute an E-value from a StatsPAI CausalResult object.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rare`	No	rare parameter (Optional[bool]).
`true`	No	true parameter (Optional[float]).
`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	Result from any StatsPAI causal estimator exposing a scalar ``estimate`` (and ideally ``se`` / ``ci``).
`measure`	No	How to interpret ``result.estimate`` (for ATE/ATT on continuous outcomes ``'SMD'`` is appropriate; pass ``'RR'`` / ``'OR'`` / ``'HR'`` for ratio estimates). Passed through to :func:`evalue`.	SMD
`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.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`rare_outcome`	No	rare_outcome parameter (Optional[bool]).
`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

B3.3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, so there is no contradiction. The description adds a useful behavioral constraint—it operates on a fitted CausalResult rather than raw estimates—but does not describe side effects, dependencies, errors, or any further runtime behavior.

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 with no filler, repetition, or embedded schema noise. It states the operation and the object type efficiently.

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?

With an output schema and 100% parameter coverage, the minimal description is adequate for a simple compute-from-result action. However, for an 11-parameter tool it misses higher-level context such as intended use after estimation, measure defaults, and the relationship to sibling E-value/sensitivity tools.

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?

All 11 parameters have schema descriptions (coverage 100%), so the baseline applies. The tool description adds no parameter-level details; the schema does the work, although some parameter descriptions (e.g. 'true parameter (Optional[float])') are tautological.

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 is a clear imperative with a specific verb ('Compute') and a precise resource/input ('an E-value from a StatsPAI CausalResult object'). It is clear in what it does, though it does not name or differentiate against siblings such as evalue, evalue_rr, or sensitivity_from_result.

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?

No sentence says when to prefer this tool over evalue/evalue_rr/evalue_rd or after which estimator it applies. The 'from_result' name implies a fitted-result context, but the description itself leaves the alternative selection to inference and does not state exclusions.

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

Deploy Server