AI-ML-Lab-MCP

Overview Schema Source Related Servers Discussions Admin

Svm Classifier

svm_classifier

Train a support vector machine classifier on a prepared train/test split with numerical, complete, scaled features and return train/test performance metrics and warnings.

Instructions

Train a support vector machine classifier. Powerful on small to medium data, slow on large data (training time grows quickly with the number of rows). Needs scaled features. The split must have only numerical, complete features. Args: split_id (str): ID of a split made by train_test_split. C (float): Regularisation: larger values fit the training data more tightly. Default is 1.0. kernel (str): "rbf", "linear", "poly" or "sigmoid". Default is "rbf"; "linear" is much faster on big data. gamma (str): Kernel width for rbf/poly/sigmoid: "scale" or "auto". Default is "scale". degree (int): Polynomial degree, only used by the "poly" kernel. Default is 3. probability (bool): Also learn class probabilities (needed for ROC-AUC on multiclass, precision-recall and roc_curve plots). It makes training several times slower. Default is True. class_weight (str, optional): "balanced" to counter imbalanced classes. Default is None. random_state (int): Seed (used for the probability calibration). Default is 42. scale (bool): Standardise the features first (strongly recommended). Default is True. Returns: dict: model_id, train/test metrics (accuracy, precision, recall, F1, ROC-AUC) and warnings.

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": {
      "split_id": "<split_id>"
    },
    "name": "svm_classifier"
  }
}

Input Schema

Name	Required	Default
`C`	No
`gamma`	No	scale
`scale`	No
`degree`	No
`kernel`	No	rbf
`split_id`	Yes
`probability`	No
`class_weight`	No
`random_state`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full load and does substantial work: it discloses training-time scaling behavior, a hard data precondition ("only numerical, complete features"), and the cost tradeoff that probability=True makes training several times slower. It omits error behavior when the split violates the precondition and says nothing about persistence of the fitted model beyond a returned model_id.

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?

Front-loaded with purpose and data-shape caveats before the argument list, and every line adds information rather than restating the schema. The docstring style repeats type/default tokens that also live in the schema, which is mildly redundant but keeps the parameter block self-contained.

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?

For a 9-parameter training tool with no annotations and no output schema, the description covers preconditions, performance costs, and the returned dict contents (model_id, metrics, warnings). Remaining gaps are failure modes — what happens if the split contains categoricals or missing values — and how the returned model_id is subsequently used.

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

Parameters5/5

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

Schema coverage is 0%, so the description must compensate, and it does so for all nine parameters — including directionality semantics (larger C fits training data more tightly), valid kernel values with a performance note, gamma being kernel-width for non-linear kernels, degree applying only to poly, and class_weight="balanced" for imbalanced classes. This is meaning the schema alone cannot supply.

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?

Opens with a specific verb and resource ("Train a support vector machine classifier") and immediately characterizes the regime it suits (small to medium data, scaled numerical features). That profile distinguishes it from the tree/boosting classifier siblings without needing to name them.

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?

Gives clear situational guidance: strong on small/medium data, slow as row count grows, requires scaled complete numerical features, and recommends the linear kernel for big data. It never explicitly routes to an alternative when the data is large or unscaled, so it stops short of naming when-not-to-use.

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

Deploy Server