Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Describe an AutoML model

describe_model
Read-onlyIdempotent

Retrieve full details of a trained AutoML model—algorithm, hyperparameters, metrics, features, and importance—to evaluate it before using predictions. Read-only.

Instructions

Get full details of one trained AutoML model: algorithm, hyperparameters, metrics, feature names, and feature importance when the algorithm provides it. Use it after list_models or train_model to judge a model before relying on predict. Read-only.

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": {
      "model_name": "<model_name>"
    },
    "name": "describe_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_nameYesModel name, as registered by `train_model` or listed by `list_models`.
include_feature_importanceNotrue = include per-feature importance scores (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.1
    • changedInput schema / properties / include_feature_importance / description
      Previous value: -"Include feature importance scores (default: true)"New value: +"true = include per-feature importance scores (default true)."
    • changedInput schema / properties / model_name / description
      Previous value: -"Model name (the one passed to `train_model`)"New value: +"Model name, as registered by `train_model` or listed by `list_models`."
  2. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the trailing "Read-only" adds nothing. What does add value beyond the annotations is "feature importance when the algorithm provides it", signalling a conditional/variable response shape the agent otherwise could not anticipate.

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?

Two sentences, front-loaded with the verb and resource, then the enumerated payload, then the usage routing. Every clause carries information; nothing is padding.

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

Completeness5/5

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

With no output schema, the description must say what comes back, and it does so concretely (algorithm, hyperparameters, metrics, feature names, feature importance). For a two-parameter read-only tool with full schema coverage and rich annotations, nothing an agent needs in order to call it correctly is missing.

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 coverage is 100%, so both parameters (model_name, include_feature_importance) are already fully self-documenting and the baseline is 3. The only added nuance is the caveat that feature importance may be unavailable depending on algorithm, which is a marginal contribution rather than a real explanation of parameter behaviour.

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?

"Get full details of one trained AutoML model" gives a specific verb (get) and resource (one trained model), then enumerates exactly what comes back: algorithm, hyperparameters, metrics, feature names, feature importance. Naming `list_models`, `train_model`, and `predict` in the same breath makes the boundary against those siblings explicit.

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?

"Use it after `list_models` or `train_model` to judge a model before relying on `predict`" states the sequencing and the decision it supports, which is genuinely actionable. It stops short of an explicit when-not (e.g. don't call it for bulk inspection, use list_models instead), so it falls just below the full 5.

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