Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

anderson_rubin_ci

Read-only

Compute Anderson-Rubin confidence sets for causal effects with instrumental variables, delivering robust inference under weak instruments. Obtain reproducible confidence intervals to support evidence-based decisions.

Instructions

Anderson-Rubin confidence set -- re-export of Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`exog`	No	exog parameter (Optional[Union[np.ndarray, pd.DataFrame, List[str]]]).
`endog`	Yes	endog parameter (Union[np.ndarray, pd.Series, str]).
`level`	No	Confidence level or reporting level.
`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
`n_grid`	No	Number of grid.
`add_const`	No	add_const parameter (bool).
`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.
`beta_grid`	No	Grid of beta values to evaluate.
`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.
`instruments`	Yes	instruments parameter (Union[np.ndarray, pd.DataFrame, List[str]]).
`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 declare readOnlyHint=true, so the agent knows this is a read-only computation. The description adds the 're-export of Validation: certified parity evidence' context, which is a useful behavioral note about provenance and reliability. However, it does not disclose what the confidence set is based on, how the grid is used, or what the output contains; the output schema presumably covers the return shape, so a 3 is fair.

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 a single compact sentence that front-loads the core purpose and adds a provenance note. It is not bloated, though it is terse enough that it could have included a bit more functional detail without becoming verbose.

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 tool with 14 parameters, 3 required, and a large sibling list, the description is too thin. It does not explain the statistical context (instrumental variables, weak-instrument robust inference), when the confidence set is appropriate, or how it relates to anderson_rubin_test. The output schema exists, so return values are covered, but the missing usage context is a significant gap.

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 schema already documents all 14 parameters. The description adds no parameter-level meaning beyond the schema. Baseline 3 is appropriate because the schema carries the burden and the description does not need to repeat it.

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 statistical object (Anderson-Rubin confidence set) and notes it is a re-export of Validation with certified parity evidence. It does not explicitly say 'computes' or 'constructs', but the name plus 'confidence set' conveys the purpose. It is distinguishable from the sibling anderson_rubin_test, which is a test rather than a confidence set, though the description does not explicitly draw that contrast.

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 on when to use this tool versus alternatives such as anderson_rubin_test, liml, or ivreg. The description does not state conditions, exclusions, or prerequisites. The only hint is the name itself, which is not enough for an agent to choose among many IV-related siblings.

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

Deploy Server