Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

finegray

Read-only

Analyze competing-risk data by fitting a proportional subdistribution hazards model, estimating covariate effects on cumulative incidence and providing diagnostics for decision next steps.

Instructions

Fine & Gray (1999) proportional subdistribution hazards model. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Covariate column names.
`tol`	No	Newton-Raphson controls.
`alpha`	No	Significance level for confidence intervals.
`cause`	No	Cause of interest (default ``1``).
`event`	Yes	Event indicator: ``0`` = censored, ``1, 2, ...`` = causes.
`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
`duration`	Yes	Follow-up-time column.
`max_iter`	No	Newton-Raphson controls.
`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://.
`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

B3.1/5.0

Behavior3/5

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

readOnlyHint=true already establishes that this is a safe read-only computation, and the description does not contradict it. The description adds the model-family behavior (subdistribution hazard estimation), but the 'Validation:' sentence reads as a metadata tag and says nothing about output, caching, or other operational behavior.

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 first sentence is concise and front-loaded with the model identity, which is good. However, the second sentence 'Validation: validated evidence tier...' is vague and does not help with invocation, so not every sentence earns its place.

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 a rich input schema, output schema, and readOnly annotation, the description is minimally sufficient to identify what the tool computes. It remains incomplete for selecting among the many survival siblings, and it omits the competing-risks guidance that would make the tool easy to invoke correctly.

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?

All 13 parameters have schema descriptions, so the baseline is 3; the tool description adds essentially no parameter-level detail. The schema's descriptions of event, cause, detail, and data_path already carry the semantics.

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 an exact statistical procedure, 'Fine & Gray (1999) proportional subdistribution hazards model', which identifies the estimator and separates it from ordinary Cox or parametric survival siblings. It lacks an explicit action verb like 'fits' or 'estimates', and the 'Validation:' tag is confusing, so it stops short of a 5.

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 sentence tells an agent when to choose Fine-Gray over alternatives such as cox, cuminc, or survreg, nor does it mention the competing-risks setting that motivates the method. The model name provides only an implicit clue, so an agent must infer usage from domain knowledge.

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

Deploy Server