MCP Machine Learning Agent

confusion_matrix_metrics

Calculate confusion matrix, accuracy, precision, and recall for two models on test data, with precision and recall for the malignant class.

Instructions

Compute the confusion matrix plus accuracy/precision/recall for both models on the test set. Precision and recall are for the malignant class. Confusion matrix order is [malignant, benign]; rows = actual, columns = predicted.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "confusion_matrix_metrics"
  }
}

Input Schema

Name	Required	Description	Default
`test_size`	No	Fraction of the data held out for testing.
`request_id`	No	Your own id for this call; recorded in the audit log.	unknown
`random_state`	No	Random seed for the train/test split.
`knn_neighbors`	No	Number of neighbors for the KNN model.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 9, 2026

TDQS

A3.7/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose two genuinely important traits: that precision/recall refer to the malignant class, and that the matrix is ordered [malignant, benign] with rows=actual, columns=predicted. However, it never says whether calling it re-trains/re-splits the models (the knn_neighbors and test_size params suggest it might), whether it is deterministic, or what the safety profile of the operation is.

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?

Three tight sentences with the core action front-loaded, and each remaining sentence adds non-obvious output semantics rather than filler. Slightly dense but no wasted text.

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 shape needn't be explained, and the description complements it with class orientation and matrix layout. The main gap is the relationship to prior training state and how this differs operationally from the prediction tools.

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 all four parameters (test_size, random_state, knn_neighbors, request_id) are already documented in the schema, and the description adds no per-parameter meaning. Baseline of 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('compute the confusion matrix plus accuracy/precision/recall') and scopes it precisely ('for both models on the test set'). This cleanly separates it from siblings like predict_logistic_regression, predict_knn, and select_best_model, which perform prediction or selection rather than evaluation.

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?

The phrase 'on the test set' and 'for both models' implies this is a post-training evaluation step, so usage is inferable but never stated. There is no explicit when-to-use, no ordering relative to train_models or select_best_model, and no statement of when not to use it.

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

Deploy Server