policy_tree

Read-only

Construct a doubly-robust policy tree from experimental data to recommend treatment decisions, with certified parity validation.

Instructions

Doubly-robust policy-tree -- article-facing alias. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`X`	No	Feature matrix or covariate DataFrame.
`d`	No	d parameter (Optional[str]).
`y`	Yes	Outcome variable column name or outcome array.
`depth`	No	depth parameter (Optional[int]).
`treat`	No	Treatment indicator or first-treatment-period column.
`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`	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://.
`max_depth`	No	max_depth parameter (Optional[int]).
`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.
`covariates`	No	Covariate matrix, DataFrame, or column names.
`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

C2.5/5.0

Behavior2/5

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

Annotations already communicate the read-only safety profile, so the description need not restate that. However, the only extra behavioral claim, 'Validation: certified parity evidence', is too opaque to tell an agent what validation is being performed, what parity is being checked, or what outputs to expect. It adds little genuinely useful behavioral context.

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 avoids unnecessary verbosity, which is good. However, 'article-facing alias' and 'certified parity evidence' are cryptic and do not clearly earn their place; the brevity reads more like under-specification than well-structured clarity.

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 complex tool with 13 parameters and a huge sibling list, this description is too incomplete. An agent cannot determine what the tool returns, how it should be invoked in a workflow, or how it relates to similar policy/doubly-robust tools. The output schema lessens the need to describe return values, but it does not make up for the missing action and usage context.

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%, and the schema provides detailed descriptions for all 13 parameters, so the baseline of 3 is appropriate. The tool description adds no parameter-level information beyond the schema, but the schema itself is sufficient for parameter semantics.

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

Purpose3/5

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

The phrase 'Doubly-robust policy-tree' names the estimator and method, but no verb or action is stated: it does not say whether the tool fits, trains, evaluates, or validates a policy tree. The 'article-facing alias' and 'Validation: certified parity evidence' fragments add little operational meaning and do not clearly distinguish it from nearby siblings such as policy_targeting, policy_value, or doubly_robust.

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?

The description gives no guidance on when to use this tool instead of the many policy-related siblings, no prerequisites, and no context about the intended workflow. Nothing is misleading, but there is also no practical usage direction.

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

Deploy Server

Causal Decision Agent