Skip to main content
Glama
Sign In
@ainize/mcp

@ainize/mcp

Official
by ainblockchain
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Training set preview

get_training_set
Read-only

Preview the questions and answers behind a training set to check whether a knowledge covers your question before paying or to show what a teaching upload actually contains.

Instructions

Preview the questions and answers behind a training set — either the one a published knowledge was trained from (use it to judge whether a knowledge covers your question before paying) or one this teaching key uploaded with create_training_set (use it to show the human what actually landed before spending a lesson). Free. A derivative set needs a teaching key (this server signs with its own when one is configured); a private one is refused with its 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": {
      "id": "<id>"
    },
    "name": "get_training_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesa knowledge id, or the dataset_id create_training_set returned
rowsNotrue = fetch the full row stream instead of the 20-row preview (public access only)
limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare only readOnly and openWorld, so the description carries most of the behavioral load, and it does: it states the call is free, that `derivative` sets need a teaching key (with the server signing when configured), and that `private` sets are refused with their metadata. The one gap is it never describes pagination/streaming behavior beyond the 20-row preview and the `rows` flag.

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?

Core purpose and cost context are front-loaded, and every clause adds information rather than restating the name. The heavy nested parentheses make it denser than necessary, but no sentence is filler.

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 3-parameter read tool with no output schema and only minimal annotations, the description covers access control, cost, and preview scope well enough to call it correctly. Return-value structure is only loosely sketched (questions and answers, 20 rows by default), which is the remaining minor gap.

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

Parameters4/5

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

With 67% schema coverage, the description adds real meaning: it clarifies that `id` is either a knowledge id or the dataset_id returned by create_training_set, implicitly mapping each id type to one of the two preview modes. It does not elaborate on `limit` or reconcile `rows` beyond what the schema already states about public access.

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?

The description opens with a specific verb and resource — preview the questions and answers behind a training set — and immediately splits it into two concrete modes (a knowledge's underlying set vs. a set uploaded by create_training_set). An agent can tell exactly what data it gets back and how this differs from the creation sibling it names.

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?

Both modes carry explicit when-to-use clauses: judge whether a knowledge covers your question before paying, and show the human what landed before spending a lesson. The exclusion for `private` sets and the key requirement for `derivative` sets add when-not conditions, so almost nothing is left to inference.

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

Deploy Server

Other Tools