Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

stochastic_dominance

Read-only

Test whether a treated distribution dominates the validation evidence tier using first- or second-order stochastic dominance. Returns diagnostic payloads to guide rollout, hold, or investigate verdicts.

Instructions

Test for stochastic dominance of the treated distribution over the Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`order`	No	Order of stochastic dominance. 1 = first-order (CDF dominance). 2 = second-order (integrated CDF dominance).
`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
`result`	Yes	Output from ``discos()`` or ``qqsynth()``.
`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.

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

C2.4/5.0

Behavior3/5

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

readOnlyHint=true already establishes that this is a non-mutating operation, lowering the burden on the description. The description adds only a vague comparison-direction/validation-tier context and does not contradict the annotations, but it does not disclose any further behavioral traits such as caching side effects or failure modes.

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

Conciseness2/5

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

The description is short, but it is structurally malformed and the parenthetical 'validated evidence tier' list is not informative. It is under-specified rather than economically specified.

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?

Even with a full input schema and output schema, the description fails to answer the core selection and invocation questions: what input should be passed, what the test compares, and how this differs from nearby siblings. The agent would have to infer critical usage details from the schema alone.

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 all eight parameters are already well documented in structured form. The description itself adds no parameter-level meaning, which is acceptable under the baseline but provides no additional value.

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

Purpose2/5

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

The description largely restates the tool name ('Test for stochastic dominance') and then appends a confusing object: 'over the Validation: validated evidence tier...' is grammatically incoherent and never identifies the comparison distribution or the hypothesis being tested. It also does not distinguish this tool from closely related siblings such as discos_test or qqsynth.

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 when-to-use guidance is provided, and no alternatives or exclusion conditions are mentioned. With many distributional and synthetic-control siblings, the agent receives no help choosing this tool over discos_test, discos, or qqsynth.

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

Deploy Server