Skip to main content
Glama

BRAINIAC Predictive & Customer Analytics

Random-forest OOB score and permutation importance

predictive-analytics_random-forest-importance
Read-onlyIdempotent

Train a small seeded random forest, report out-of-bag accuracy or R², and estimate permutation feature importance with Fisher-Yates shuffles. Price $0.05 USDC. POST /api/v1/predictive-analytics/random-forest-importance. An unpaid call returns the x402 payment terms and does not run.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>",
      "columns": "<columns>",
      "rows": "<rows>",
      "target": "<target>"
    },
    "name": "predictive-analytics_random-forest-importance"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesrows, array. Required.
seedNoseed, integer, from -9007199254740991 to 9007199254740991. Required.
taskYestask, string, one of classification, regression. Required.
treesNotrees, integer, from 10 to 500. Required.
targetYestarget, array. Required.
columnsYescolumns, array. Required.
maxDepthNomaxDepth, value. Required.
maxFeaturesNomaxFeatures, value. Required.sqrt
minSamplesLeafNominSamplesLeaf, integer, from 1 to 1000. Required.
permutationRepeatsNopermutationRepeats, integer, from 1 to 50. Required.

Output Schema

NameRequiredDescriptionDefault
capsNocaps. Object.
seedNoseed. Number.
sourcesNosources. Array.
oobScoreNooobScore. Number.
rowsUsedNorowsUsed. Number.
importanceNoimportance. Array.
droppedRowsNodroppedRows. Number.
limitationsNolimitations. Array.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety bar is lower. The description still adds genuinely useful behaviour beyond them: the model is 'small' and 'seeded', the cost is $0.05 USDC, the transport is POST to a named path, and an unpaid call returns x402 payment terms without running. It does not discuss runtime, row limits, or determinism guarantees across seeds, so it falls short of 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero padding. The core capability comes first, followed by the operational facts (price, endpoint, unpaid behaviour), so an agent gets the essential picture from the opening clause. Nothing is repeated from the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the annotations cover the safety profile. For a 10-parameter modelling tool the description supplies the compute semantics, cost, and payment flow that structured fields cannot express. The remaining gap is selection guidance against sibling modelling and metrics tools, which matters given the crowded predictive-analytics family.

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 already documents all ten parameters and the baseline of 3 applies. The description contributes only indirect hints, namely that the forest is seeded (seed) and that importance is estimated with Fisher-Yates shuffles (permutationRepeats). It gives no guidance on meaningful ranges, defaults, or how maxFeatures and minSamplesLeaf trade off against accuracy.

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: train a seeded random forest, report out-of-bag accuracy or R², and estimate permutation feature importance. That is far more than a restatement of the title. It stops short of 5 because it never distinguishes itself from siblings such as decision-tree-train or classification-metrics, so the agent must infer the boundary.

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

Usage Guidelines3/5

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

Usage is implied by the described outputs (OOB accuracy for classification, R² for regression, importance ranking), which tells an agent roughly what the tool is for. There is no explicit when-to-use or when-not-to-use guidance and no named alternative, even though decision-tree-train and classification-metrics are close neighbours. The payment note does clarify what happens on an unpaid first call, which is invocation guidance of a sort.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources