Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

tF_adjustment

Read-only

Compute weak-instrument-robust critical values from the first-stage F statistic to correct hypothesis tests.

Instructions

tF adjusted critical value (Lee, McCrary, Moreira & Porter 2022, AER).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`alpha`	No	Significance level for confidence intervals and tests.
`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.
`first_stage_F`	Yes	first_stage_F parameter (float).

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

D1.9/5.0

Behavior2/5

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

Annotations provide readOnlyHint=trueional and openWorldHint=false, covering safety and determinism. The description adds a citation to a specific paper, which hints at the statistical method used, but it does not disclose the nature of the output (single number, table, or object), any assumptions, or edge-case behavior. This is minimal added context beyond annotations.

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 extremely short (one phrase), but it is under-specified rather than concise. It lacks any structural elements like a verb or context. There is no front-loading of critical information beyond the tool's name itself, and it fails to earn its place as a useful explanation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 8 parameters (including many generic data-handling ones) and an output schema, the description provides almost no contextual information. It does not explain the statistical setting, what the adjusted critical value is used for, how it relates to first_stage_F, or when an agent would invoke it. The citation is the only meaningful context, but it is insufficient for correct invocation without prior domain knowledge.

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. However, the description itself adds no additional meaning to any parameter. Even the schema description for the required 'first_stage_F' is tautological ('first_stage_F parameter (float)'), so the description provides no enrichment, but does not detract either.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'tF adjusted critical value (Lee, McCrary, Moreira & Porter 2022, AER)' is essentially a noun phrase that restates the tool name. It implies the tool computes a critical value, but it lacks an explicit verb (e.g., 'Computes', 'Returns') and does not clarify what the value is for or how it differs from the sibling tF_critical_value beyond the word 'adjusted'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool over alternatives. The sibling tF_critical_value likely provides the unadjusted counterpart, but the description does not mention it or any conditions that would select one over the other. No context or exclusions 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