Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

policy_targeting

Read-only

Identify which units to treat under a budget constraint using effect estimates, maximizing total impact while respecting treatment limits and minimum effect thresholds.

Instructions

Rank-and-treat policy under a budget constraint.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cate`	Yes	Per-unit effect estimates -- a raw array, a ``metalearner()`` / ``tarnet()`` result, or a fitted ``causal_forest()`` model (training-sample effects are used).
`frac`	No	Maximum fraction of units that can be treated (in ``(0, 1]``).
`budget`	No	Maximum number of units that can be treated. Mutually exclusive with ``frac``.
`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`	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.
`min_effect`	No	Never treat a unit whose predicted effect is at or below this threshold, even with budget left over -- treating predicted non-responders wastes budget and can do harm.
`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

B3.2/5.0

Behavior3/5

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

readOnlyHint=true already covers the safety profile, and the description adds the behavioral idea of ranking units and treating under a budget. However, it does not disclose optional chaining behavior such as as_handle caching or result_id reuse, though the output schema covers return-value expectations.

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

Conciseness5/5

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

The description is a single seven-word sentence with no filler and front-loads the core operation and constraint. It is highly concise even though its terseness costs points in other dimensions.

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 10-parameter tool in a massive sibling set, this one-liner is too thin: it omits the typical input source (CATE estimates), the frac-versus-budget decision, and any relationship to policy_tree or policy_value. The schema covers mechanics, but tool-level selection context is incomplete.

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 parameters are already well documented. The description itself adds no extra parameter semantics beyond loosely echoing the concepts of ranking, treatment, and budget.

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 active phrase 'Rank-and-treat policy' plus 'under a budget constraint' conveys a specific operation: assign treatment to the highest-effect units up to a budget limit. It is clear and not a tautology, but it does not explicitly differentiate from sibling tools like policy_tree or policy_value.

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 explicit when-to-use or when-not-to-use guidance, and it names no alternatives despite a very large sibling set containing policy_tree, policy_value, and offline_safe_policy. The 'budget constraint' phrase is only an implicit cue.

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

Deploy Server