Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

glm

Read-only

Fit a generalized linear model to your data, validating assumptions and delivering certified parity evidence for evidence-backed business decisions.

Instructions

Fit a Generalized Linear Model. Validation: certified parity evidence.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoNames of independent variables (alternative to formula).
yNoName of the dependent variable (alternative to formula).
tolNoConvergence tolerance on the relative change in deviance.
linkNoLink function. If ``None`` the canonical link for the chosen family is used. Options: ``"identity"``, ``"log"``, ``"logit"``, ``"probit"``, ``"inverse"``, ``"cloglog"``, ``"power"``, ``"sqrt"``.
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
familyNoDistribution family. One of ``"gaussian"``, ``"binomial"``, ``"poisson"``, ``"gamma"``, ``"inverse_gaussian"``, ``"negative_binomial"``.gaussian
offsetNoVariable name for offset.
robustNoStandard-error type (``"nonrobust"``, ``"hc0"``-``"hc3"``, ``"hac"``).nonrobust
clusterNoVariable name for clustered standard errors.
formulaNoModel formula (e.g. ``"y ~ x1 + x2"``).
maxiterNoMaximum number of IRLS iterations.
weightsNoVariable name for observation weights.
exposureNoVariable name for exposure (``log(exposure)`` is added as offset).
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.
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

C2.8/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=true, so the description need not repeat that. But the description adds no behavioral context beyond a vague 'Validation' phrase, and it fails to mention important side effects like server-side caching via as_handle, or what 'certified parity evidence' actually means.

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 core sentence is concise and front-loaded. However, the second sentence 'Validation: certified parity evidence' is cryptic and does not earn its place; it likely confuses rather than helps 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?

With 19 parameters, a rich output schema, and dozens of closely related sibling tools, this sparse description is insufficient. An agent cannot determine when to choose this tool, how it relates to alternatives, or what a typical call workflow looks like.

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 schema fully documents all 19 parameters. The description itself adds no parameter-level meaning beyond the model name, so the baseline score 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 names a specific verb and resource: 'Fit a Generalized Linear Model.' This clearly identifies the operation. However, it does not differentiate from close siblings like feglm, logit, probit, or regress, so an agent cannot distinguish which estimator to pick without inspecting schemas.

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 the many alternative regression/GLM tools in the sibling list, and no mention of prerequisites, exclusions, or fallback conditions. The 'Validation: certified parity evidence' phrase does not provide usage context.

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