Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

List AutoML models

list_models
Read-onlyIdempotent

Lists trained AutoML models filtered by status and optional task type, helping you find a model name to use with predictions.

Instructions

List the AutoML models this tenant has trained, filtered by status (default deployed) and optionally task type, and return {models: [{name, task_type, status, version, created_at}], count}. Use it to find a model name for predict; use describe_model for accuracy, hyperparameters and feature importance. Read-only.

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": "list_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
statusNoOnly return models with this status (default deployed).deployed
task_typeNoOnly return models of this task type, e.g. binary_classification or regression.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.1
    • changedInput schema / properties / status / description
      Previous value: -"Optional filter: only return models with this status (default: deployed)"New value: +"Only return models with this status (default deployed)."
    • changedInput schema / properties / task_type / description
      Previous value: -"Optional filter: only return models with this task_type"New value: +"Only return models of this task type, e.g. binary_classification or regression."
  2. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; "Read-only." largely restates them. The description does add genuine behavioral value beyond the annotations: the non-obvious fact that omitting `status` silently restricts results to deployed models, plus the exact return envelope. It stops short of covering pagination or result limits, which matters for a listing tool.

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?

Single tight package: purpose, filters, return shape, routing to predict and describe_model, then a safety tag — all front-loaded with zero filler sentences. Only the trailing read-only clause slightly duplicates the annotations.

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?

With no output schema, the description correctly supplies the return shape ({models: [...], count}) including field names, which is exactly what is needed for a list tool. Minor gaps remain around result-set size or truncation behavior when many models exist.

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 are already self-documenting; baseline 3 applies. The description reinforces the consequential default (status=deployed) but adds no syntax or format detail for task_type beyond the example values already present in the schema.

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?

Description gives a specific verb and resource ("List the AutoML models this tenant has trained") plus a precise scope qualifier (filtered by status, default deployed) and names the sibling it is not (describe_model). An agent can distinguish it from describe_model and predict without opening any schema.

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

Usage Guidelines5/5

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

Explicitly states the primary use case ("find a model name for `predict`") and hands off the non-overlapping use case to a named alternative ("use `describe_model` for accuracy, hyperparameters and feature importance"). Both when-to-use and when-to-use-something-else are covered.

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