Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

icc

Read-only

Calculate intra-class correlation from a fitted mixed model to quantify how much variance a random effect explains, with confidence intervals and validation evidence.

Instructions

Intra-class correlation for a fitted mixed model. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNoRNG seed forwarded to :func:`numpy.random.default_rng`.
alphaNoSignificance level for the confidence interval. Default 0.05.
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
n_bootNoNumber of parametric bootstrap replicates used to compute the CI. ``0`` (default) uses the delta-method approximation on the log-variance scale, which is faster and usually within a few decimals of the parametric-bootstrap answer for moderate N.
resultYesA ``MixedResult`` returned by :func:`statspai.mixed`.
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.
componentNoName of the random-effect variance to put in the numerator. Defaults to the random intercept (``"_cons"``)._cons
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

B3.3/5.0
Behavior3/5

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

Annotations indicate readOnlyHint=true and openWorldHint=false, so the description need not state read-only. It adds minimal behavioral context: the validation tier mentioned seems irrelevant and confusing. It doesn't disclose the bootstrap process or delta-method behavior, but parameter descriptions in the schema do cover that. No contradiction with annotations.

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, which is concise, but the second sentence about validation is cryptic and wastes valuable space. The first sentence is directly relevant. It could be improved by adding usage guidance without significant length increase.

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?

Given the tool's moderate complexity (11 params, output schema present), the description is sparse. It fails to mention that the tool expects a MixedResult object or handle, and doesn't hint at the bootstrap vs. delta-method trade-off, even though those are in schema. The validation sentence is unclear and doesn't help completeness. Overall, it's minimally complete but leaves the agent to infer key usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds some semantic value by indicating the tool operates on a fitted mixed model, which clarifies the 'result' and 'result_id' parameters' context. It also implicitly relates 'component' and 'alpha' to the ICC computation, but doesn't elaborate beyond schema.

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 clearly states the tool computes intra-class correlation for a fitted mixed model, with a specific verb and resource. It distinguishes it from siblings like 'mixed' (which fits the model) and other post-estimation tools, though it doesn't explicitly name a sibling. The validation sentence seems out-of-place and not directly related to the action.

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 does not provide when-to-use guidance or contrast with alternatives. It doesn't mention that it requires a fitted 'MixedResult' from the 'mixed' tool, nor when to choose this over other post-estimation tools. The presence of result_id and result parameters implies a prerequisite, but that's left to the schema.

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