Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

demean

Read-only

Apply within-transformation to strip fixed effects from your regressors, producing the adjusted variable and keep mask for reliable causal analysis.

Instructions

Return the within-transformed x and the singleton keep mask. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`fe`	Yes	fe parameter (Union[pd.DataFrame, np.ndarray, None]).
`tol`	No	Numerical convergence tolerance.
`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
`slopes`	No	slopes parameter (Optional[Sequence[SlopeSpec]]).
`solver`	No	solver parameter (str).	map
`maxiter`	No	maxiter parameter (int).
`weights`	No	Observation weights.
`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.
`drop_singletons`	No	drop_singletons parameter (bool).

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

C2.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds only the cryptic 'Validation: certified parity evidence' which is unclear and does not disclose any behavioral trait beyond what annotations provide. No contradiction.

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 extremely concise with no wasted words, and the main purpose is front-loaded. It is appropriately short, though it borders on under-specification.

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?

Given the tool's complexity (14 parameters, many siblings) and the presence of an output schema, the description is inadequate. It fails to explain when to use this transformation, what the 'singleton keep mask' means, or how it fits into a causal inference pipeline. An agent would struggle to know when to invoke this tool.

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 each parameter is already documented. The description adds no parameter-specific meaning, and the baseline of 3 applies because the schema does the heavy lifting.

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 ('Return') and resource (within-transformed x and singleton keep mask), making the core function clear to a technical audience. However, it uses jargon ('within-transformed', 'singleton keep mask') without explaining the econometric context, and it does not differentiate from closely related tools like absorb_ols or feols.

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?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusion criteria. With over 500 sibling tools, the lack of any usage context leaves an agent unable to decide if demeaning is the right step.

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

Deploy Server