Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

kitagawa_decompose

Read-only

Decompose a rate difference between two groups into composition and rate components. Identifies how much of the gap comes from group composition versus category-specific rates.

Instructions

Kitagawa (1955) two-factor rate decomposition. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`by`	Yes	Category variable(s) defining cells.
`rate`	Yes	Column holding the category-specific rate (or 0/1 outcome at the individual level).
`group`	Yes	Binary group indicator.
`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
`weights`	No	Cell population weights. If None, each row treated as individual-level data (weight = 1).
`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://.
`normalize`	No	- 'a': rate effect evaluated at A's composition - 'b': rate effect evaluated at B's composition - 'symmetric': average (default)	symmetric
`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

Behavior3/5

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

The readOnlyHint annotation already establishes that this is a non-mutating computation, so the description does not need to restate that. The added 'certified parity evidence' note hints at validation behavior but is cryptic and does not meaningfully disclose operational details, though it does not contradict the annotations.

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

Conciseness4/5

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

The description is only two short sentences and avoids repeating schema content or parameter details. The method name is front-loaded, but the second 'Validation' sentence is opaque and adds limited clarity, preventing a perfect score.

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 rich input schema, output schema, and readOnly annotation, the description is minimally viable for invoking the tool correctly. It is less complete for helping an agent choose among the many decomposition-related siblings or understand the intended interpretation of the two-factor decomposition, but the schema fills most technical gaps.

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 schema description coverage is 100%, so the input schema already documents all 11 parameters thoroughly. The description adds no parameter-level semantics beyond naming the decomposition method, which matches the baseline for full schema coverage.

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 names the method (Kitagawa 1955) and the resource/action (two-factor rate decomposition), which is specific enough to identify what the tool does. It differentiates the tool from generic decomposition siblings by method name, though it does not elaborate on what the two factors are.

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 'two-factor rate decomposition' implies this tool is appropriate when a Kitagawa-style rate decomposition is needed, and the method name distinguishes it from related decomposition tools. However, there is no explicit when-to-use or when-not-to-use guidance, nor any mention of alternative tools.

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

Deploy Server