Skip to main content
Glama

export_model

Saves a trained model together with its preprocessing pipeline and metadata as a reusable artifact for later predictions.

Instructions

Save a trained model with preprocessing pipeline and metadata.

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": {
      "artifact_name": "<artifact_name>"
    },
    "name": "export_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoDataset filename (to train and export).
stratifyNoStratify split (classification only).
task_typeNo'classification' or 'regression'.
test_sizeNoTest fraction (default 0.2).
model_nameNoModel to train and export.
model_handleNoHandle of a previously trained model.
random_stateNoRandom seed (default 42).
artifact_nameYesName for the saved artifact.
target_columnNoTarget variable column.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden and falls well short. It never says where the artifact is written, what format it takes, whether an existing artifact with the same name is overwritten, or what happens when model_handle is omitted versus provided; only the bundled contents (pipeline, metadata) are disclosed.

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?

A single front-loaded sentence with no filler, so nothing is wasted. The problem is under-specification rather than verbosity, which keeps it out of the top score.

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

Completeness2/5

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

For a nine-parameter tool with no annotations and no output schema, one sentence about saving is not enough. The description neither explains the training inputs the schema demands nor describes the returned or persisted artifact beyond naming its parts.

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 baseline is 3, and the description does not enlarge on any parameter. The train-versus-reuse ambiguity between model_name and model_handle would have been the most valuable clarification and is left entirely to the schema's one-line hints.

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?

States a specific verb and resource ('Save a trained model') plus what the artifact bundles ('preprocessing pipeline and metadata'). However, the nine parameters (name, model_name, task_type, test_size, stratify, target_column) show the tool also trains a model, which the sentence never mentions, and it does not distinguish itself from siblings like train_baseline or compare_models.

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?

No guidance on when to choose this over train_baseline, prepare_dataset, or predict, and no prerequisites such as whether a model must already exist. The schema exposes both model_name (train) and model_handle (reuse) paths, but the description gives no hint about which situation calls for which.

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