Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

evalue_rd

Read-only

Compute exact E-value for a risk difference from a 2x2 table, quantifying how much unmeasured confounding would be needed to explain the observed effect.

Instructions

Exact E-value for a risk difference from a 2x2 table.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`n00`	Yes	Unexposed cases and unexposed non-cases.
`n01`	Yes	Unexposed cases and unexposed non-cases.
`n10`	Yes	Exposed cases and exposed non-cases.
`n11`	Yes	Exposed cases and exposed non-cases.
`grid`	No	Step size of the bias-factor grid search for the CI E-value.
`true`	No	Reference risk difference (must be <= the observed RD).
`alpha`	No	Significance level for the confidence-limit E-value.
`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
`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.
`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

B3.4/5.0

Behavior2/5

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

The annotations already declare readOnlyHint=true, so no side-effect disclosure is required. The description adds no behavioral detail beyond the core purpose, omitting the grid search behavior, output payload options, and chaining behavior that appear in the schema.

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 or repetition. It communicates the tool's purpose immediately and every word earns its place.

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?

Given 13 parameters, 4 required, and extra generic data-loading arguments, a one-sentence description is insufficient. The output schema covers return values, but the main gaps—cell naming conventions, when to use this versus sibling E-value tools, and how to supply data—remain unaddressed.

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 baseline is 3 even though the tool description says nothing about parameters. However, the required cell descriptions are ambiguous and duplicated (n00/n01 and n10/n11 share the same text), and the description does not clarify the 2x2 cell orientation.

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 names a specific operation ('Exact E-value'), the target estimand ('risk difference'), and the required data structure ('2x2 table'). This is specific enough to distinguish it from sibling tools like evalue_rr or general evalue tools, even without naming them.

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 'from a 2x2 table' implies the input context and is a weak usage cue. However, there is no explicit statement of when to prefer this tool over evalue_rr or other E-value/sensitivity tools, and no exclusions or alternatives are given.

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

Deploy Server