Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

clogit

Read-only

Analyzes choice data using conditional logit to estimate how alternative-specific covariates influence selection, delivering certified parity evidence for rollout or hold decisions.

Instructions

McFadden's conditional (fixed-effect) logit for choice data. Validation: certified parity evidence.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoAlternative-specific (and/or individual-specific interacted with alternative dummies) covariates.
yNoBinary indicator: 1 = chosen, 0 = not chosen.
tolNoNumerical convergence tolerance.
alphaNoSignificance level for confidence intervals and tests.
groupNoVariable identifying the choice set / decision-maker.
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
robustNoRobust standard-error or covariance estimator option.nonrobust
clusterNoCluster identifier column for clustered standard errors.
formulaNoFormula ``"chosen ~ price + quality"``.
maxiterNomaxiter parameter (int).
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

B3.4/5.0
Behavior2/5

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

The description adds no operational behavior beyond the model name; the 'Validation: certified parity evidence' sentence is a trust claim, not a disclosure of what the tool does at runtime. Annotations already provide readOnlyHint, so the safety profile is covered, but the description itself contributes little behavioral context.

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 very short and front-loads the model identity in the first sentence. The second sentence is not actionable for tool selection, but the overall size is economical and not padded.

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?

For a 15-parameter estimator the description is minimal, but the input schema and output schema are rich, so the agent can recover parameter semantics and return structure. It still lacks guidance on required inputs and how to choose this over sibling choice models, leaving clear 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%, with every parameter documented, including defaults and enums. The description adds no parameter-level meaning, so it earns the baseline 3 rather than higher.

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 estimator, McFadden's conditional (fixed-effect) logit, and the target data type, choice data, which distinguishes it from plain logit, cloglog, and panel logit siblings. It lacks an explicit action verb such as 'estimate' or 'fit', so it is clear but not maximally explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'For choice data' plus 'conditional (fixed-effect)' provides a clear context for when to select this tool. It does not name alternatives or exclusion criteria, so it falls short of explicit when-to-use/when-not-to-use 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