Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

mediation

Read-only

Estimate direct and indirect effects in causal mediation analysis to determine whether a mediator explains the treatment-outcome relationship, with diagnostics and next steps for decisions.

Instructions

Causal-mediation analysis -- article-facing alias for Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`X`	No	Feature matrix or covariate DataFrame.
`d`	Yes	d parameter (str).
`m`	Yes	m parameter (str).
`y`	Yes	Outcome variable column name or outcome array.
`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`	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

C2.4/5.0

Behavior2/5

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

readOnlyHint=true and openWorldHint=false already convey the safety profile, so the description does not need to restate that. However, it adds no behavioral detail beyond the annotations; 'certified parity evidence' is too vague to inform the agent about what happens when the tool runs, what it returns, or what validations it performs.

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

Conciseness2/5

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

The description is short, which is good, but the second half is a confusing alias clause that does not earn its place. It is under-specified rather than effectively concise, and it front-loads domain vocabulary without explaining it.

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 10 parameters, 4 required fields, an output schema, and a large sibling list, a single cryptic phrase is insufficient context. The description fails to explain what the core columns d, m, and y are, what 'parity evidence' means, or how this tool relates to mediation_decompose/mediate, though output schema and annotations do cover some return and safety aspects.

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 baseline is 3 even without parameter information in the description. Yet several schema entries are tautological ('d parameter (str)', 'm parameter (str)'), and the description itself adds nothing to clarify what d, m, y, or X actually mean in the mediation context.

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 names the domain ('Causal-mediation analysis'), so it is not a pure tautology of the tool name 'mediation'. However, it is not a verb+resource statement and it does not differentiate this tool from closely related siblings like mediation_decompose, mediate, or mediate_interventional. The appended phrase 'article-facing alias for Validation: certified parity evidence' is cryptic and does not clarify the tool's purpose.

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 guidance is provided about when to use mediation versus the many related mediation or validation tools. The description neither states conditions nor names alternatives, leaving the agent to choose based solely on the tool name.

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

Deploy Server