Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

quasi_untreated_test

Read-only

Check for quasi-untreated groups at specified doses, validating their evidence tier to support causal decision-making.

Instructions

Test that quasi-untreateded groups exist (dCDH et al., Section 3.3). Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dose`	Yes	Doses at the horizon being tested. Non-positive values are
`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

B3.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds the validation-tier concept and the existence-check purpose, but does not disclose details like what happens on failure, how the test is computed, or any constraints beyond the read-only nature. It adds modest context but not rich behavioral insight.

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

Conciseness3/5

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

The description is two sentences and front-loaded, but the second sentence about validation tier is cryptic and the first contains a typo ('untreateded'). It is concise but not perfectly clear; every sentence carries some weight but the typo and vague validation phrase reduce effectiveness.

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?

Given the output schema exists and annotations cover read-only behavior, the description is minimally sufficient but lacks detail about the test's methodology, expected output semantics, or when it applies. For a tool with 7 parameters and a specific niche purpose, more context would help an agent decide to call it, but it is not grossly incomplete.

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%, with each parameter having a description in the input schema. The tool description does not add any additional meaning to parameters. The dose description is truncated ('Non-positive values are'), but that is a schema issue, not something the description compensates for. Baseline 3 is appropriate since the schema already documents all parameters.

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 states a specific verb ('Test that quasi-untreateded groups exist') and references a source (dCDH et al., Section 3.3), making the core purpose clear. However, it does not differentiate from the many sibling test tools (e.g., reset_test, ri_test, functional_form_test) beyond the unique subject, and the misspelling 'untreateded' slightly undermines clarity.

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?

The description provides no guidance on when to use this tool versus alternatives. It mentions a validation tier but does not explain selection criteria, prerequisites, or scenarios where this test is appropriate. There is no explicit when-not-to-use or reference to sibling tests.

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

Deploy Server