Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

pipeline_iv

Read-only

Run an end-to-end instrumental variable analysis: ivreg, first-stage F tests, Anderson-Rubin CI, and e-value, returning a markdown report and result ID.

Instructions

End-to-end IV workflow: ivreg -> first-stage F (effective + Olea-Pflueger) -> Anderson-Rubin CI -> e-value. Returns one markdown report + result_id.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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
`formula`	Yes	'y ~ x_exog + (d_endog ~ z_instrument)' style.
`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

A3.8/5.0

Behavior3/5

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

The description discloses the multi-step workflow and the return payload, which adds context beyond the readOnlyHint annotation. However, it states result_id is returned unconditionally, while the schema ties result_id/result_uri to as_handle=true, leaving some ambiguity about the actual output contract.

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 dense sentence that front-loads the workflow components and ends with the output. Every phrase contributes useful information with no filler.

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?

For a 7-parameter tool with a fully documented schema and an output schema, the description provides sufficient context about what the pipeline does and what it returns. The main gap is explicit usage routing versus the component tools, which is already captured in usage_guidelines.

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?

The input schema has 100% description coverage, so the baseline applies. The description adds workflow-level context but does not provide additional meaning for individual parameters such as formula, data_path, or detail levels.

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 clearly identifies a composite IV workflow by naming the exact component chain (ivreg -> first-stage F -> Anderson-Rubin CI -> e-value) and the output (markdown report + result_id). This makes it readily distinguishable from siblings such as ivreg, effective_f_test, anderson_rubin_ci, and evalue.

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 'End-to-end IV workflow' implies use when a complete IV pipeline is desired, but it does not explicitly state when to choose this over calling ivreg, effective_f_test, anderson_rubin_ci, and evalue separately. There are no exclusions or alternative routing hints.

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

Deploy Server