Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

logit

Read-only

Estimates logistic regression models by maximum likelihood for binary outcomes, supplying coefficients, confidence intervals, and diagnostics to validate evidence for causal decisions.

Instructions

Logit (logistic) regression via maximum likelihood. Validation: certified parity evidence.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoRegressor names (alternative to formula).
yNoDependent variable name (alternative to formula).
tolNoConvergence tolerance on log-likelihood change.
alphaNoSignificance level for confidence intervals.
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``'nonrobust'`` for MLE SE, ``'hc1'`` / ``'robust'`` for sandwich SE.nonrobust
clusterNoColumn name for clustered standard errors.
formulaNoFormula like ``"y ~ x1 + x2"``.
maxiterNoMaximum Newton-Raphson iterations.
weightsNoColumn name for frequency/analytic weights.
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.
at_valuesNoVariable values for ``marginal_effects='at'``.
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.
odds_ratioNoReport odds ratios instead of log-odds coefficients.
data_columnsNoOptional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
data_sample_nNoOptional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
marginal_effectsNo``'average'`` (AME), ``'mean'`` (MEM), or ``'at'`` (MER).

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 indicate readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds 'via maximum likelihood' and 'certified parity evidence,' which gives some context about the estimator and validation, though the second phrase is opaque and not fully actionable.

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 short and front-loaded, but the second sentence is cryptic ('Validation: certified parity evidence') and does not clearly earn its place. It is concise, yet that conciseness sacrifices useful guidance.

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 tool with 18 parameters and many close siblings, the description is notably incomplete. It does not mention that the outcome should be binary, explain when logit is preferred over probit/ologit, or hint at the required data shape. The presence of an output schema does not compensate for these practical gaps.

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 parameters thoroughly. The description adds no additional parameter-level meaning, but the baseline of 3 is appropriate because the schema carries the full burden.

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 states a specific verb and resource ('Logit (logistic) regression via maximum likelihood'), making the core purpose clear. It does not explicitly differentiate from close siblings like probit, ologit, or panel_logit, but the 'logit' and 'maximum likelihood' wording gives an agent a solid baseline.

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 guidance on when to use this tool versus alternatives such as probit, ologit, or panel_logit. No exclusions, conditions, or alternative routes are mentioned; the phrase 'Validation: certified parity evidence' is not usage guidance.

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