Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

gelbach

Read-only

Decompose omitted variable bias in regression coefficient changes using Gelbach's method, quantifying each added variable's contribution.

Instructions

Gelbach (2016) decomposition of omitted variable bias. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable name.
`vce`	No	Heteroskedasticity-robust or homoskedastic covariance, as ``b1x2 ..., robust`` and plain ``b1x2``. Standard errors were a two-term delta method that treated the auxiliary and long-regression estimates as independent; ``b1x2`` keeps their covariance. On ``cps_wage`` that moved the SEs by 0.03%, but the old formula has no guarantee of being that close. Point estimates are unchanged.	robust
`alpha`	No	Significance level.
`base_x`	Yes	Variables in the base (short) specification.
`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
`added_x`	Yes	Variables added to obtain the full (long) specification.
`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.
`var_of_interest`	No	Which base variable's coefficient change to decompose. Defaults to the first element of ``base_x``.

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

C2.8/5.0

Behavior2/5

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

The annotations already indicate readOnlyHint=true and openWorldHint=false, so the agent knows the tool is read-only. The description adds no behavioral context beyond that, and the vague 'Validation: certified parity evidence' does not explain side effects, required data formats, or any runtime characteristics. No contradiction with annotations.

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 short and front-loaded with the method name, but the second sentence ('Validation: certified parity evidence') is cryptic and does not clearly earn its place. It is not wasteful, but it is also not genuinely useful, making the overall structure merely adequate.

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?

For a 12-parameter, 4-required-parameter tool with an output schema, the description is too sparse. It lacks any context about when to apply the decomposition, what inputs are expected in terms of model specification, or how to interpret the result. Although the schema and output schema carry some weight, an agent would be poorly equipped to decide when and how to call this tool without richer descriptive guidance.

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 input schema fully documents all 12 parameters. The tool description adds no parameter-level information, which is acceptable given the schema's completeness. Baseline 3 applies.

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 a specific method (Gelbach 2016) and its purpose (decomposition of omitted variable bias), which distinguishes it from other decomposition tools like oaxaca or kitagawa_decompose. However, it lacks an explicit verb (e.g., 'computes') and reads as a noun phrase, leaving the action implied rather than stated.

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 given about when to use this tool versus alternatives. The description does not mention prerequisites, model fit requirements, or scenarios where Gelbach decomposition is appropriate. The second sentence about 'certified parity evidence' provides no usage context.

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

Deploy Server