Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

postestimation_contract

Read-only

Discover which post-estimation actions are available for a fitted result, so you can choose the next analytical step.

Instructions

Return the post-estimation actions supported by result.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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	Fitted StatsPAI result, estimator, or compatible object.
`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.
`include_diagnostics`	No	Include scalar diagnostics from ``model_info`` / ``diagnostics``.

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

Behavior2/5

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

The description adds no behavioral detail beyond the annotations; readOnlyHint and openWorldHint already signal a safe read operation. It does not mention side effects, caching, validation, or that the tool introspects a fitted result without running an estimator, so it contributes little beyond what structured fields already say.

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 front-loaded sentence with no filler, making it easy to scan. It is concise but very thin, so while structure is clean, it isn't an exemplary informative description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema and fully documented parameters, the main missing piece is usage context: what a 'contract' contains, when to call this vs postestimation_report/estat, and that it supports planning subsequent calls. The schema's detail parameter hints at suggested_functions, but the description itself leaves the agent to infer the tool's role.

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 itself provides detailed meaning for every parameter (e.g., detail depth, as_handle caching, data loading options). The description adds no parameter-level semantics, so the baseline of 3 is appropriate.

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 identifies a specific verb ('Return') and resource ('post-estimation actions supported by *result*'), so an agent can tell what the tool does. It is clear but does not contrast itself with sibling tools such as postestimation_report or estat, so it does not earn the top score.

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?

There is no statement about when to call this tool versus alternatives. It neither names siblings like postestimation_report or estat nor gives conditions such as 'after fitting a model to discover available commands,' leaving the agent to infer usage from the name.

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

Deploy Server