Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

cox

Read-only

Estimate survival and hazard ratios with proportional hazards regression, including tie handling, stratification, and robust standard errors, to support evidence-based decisions.

Instructions

Cox Proportional Hazards model via partial likelihood. Validation: certified parity evidence.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoCovariate column names (overrides formula RHS).
tiesNoTie-handling method: ``'efron'`` or ``'breslow'``.efron
alphaNoSignificance level for confidence intervals.
eventNoColumn name for event indicator (1 = event, 0 = censored).
detailNoPayload 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
robustNo``'hc0'`` for sandwich SE.nonrobust
strataNoColumn name for stratification variable.
clusterNoColumn name for cluster-robust SE.
formulaNoFormula of the form ``'duration ~ x1 + x2'``. If given, ``duration`` is inferred from the LHS.
durationNoColumn name for follow-up time (overrides formula LHS).
as_handleNoIf 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_pathNoAbsolute 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_idNoOptional 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_columnsNoOptional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
hazard_ratioNoIf True, report hazard ratios in the summary alongside coefficients.
data_sample_nNoOptional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds the estimation method ('via partial likelihood'), which is a useful behavioral detail, but the 'Validation: certified parity evidence' phrase is vague and does not meaningfully disclose behavior such as output structure, censoring handling, or default settings.

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 very short and front-loaded with the model type, which is good. However, the sentence 'Validation: certified parity evidence.' is cryptic and does not clearly earn its place, and the overall terseness leaves out useful framing for an agent.

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 16-parameter survival model, the description is too thin. It does not explain when Cox regression is appropriate, how it relates to censoring and duration/event columns, or why an agent should choose this over cox_frailty, aft, or survreg. The schema fills parameter details, but the high-level modeling context is missing.

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 input schema already documents all 16 parameters and their roles. The description itself adds no parameter-level meaning beyond identifying the model type, matching the baseline for high schema coverage.

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 the tool as a Cox Proportional Hazards model via partial likelihood, which clearly indicates the modeling approach and target resource. However, it lacks a specific verb like 'fit' or 'estimate', and it does not differentiate this tool from related siblings such as cox_frailty, aft, or survreg.

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 provides no guidance on when to use this tool versus alternatives like aft, cox_frailty, or survreg. There are no exclusion criteria, no prerequisites, and no mention of suitable data scenarios, so the agent receives no usage direction beyond the tool's name.

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

Deploy Server

Other Tools