Skip to main content
Glama

cv_load_dataset

Download a Kaggle dataset or competition to the runtime and unzip it for immediate use in training or analysis.

Instructions

Download a Kaggle dataset or competition onto the runtime and unzip it.

ref: "owner/dataset-slug" for datasets, or the competition slug for competitions. kind: "dataset" or "competition". Works when this computer is logged in to Kaggle (the login is used for this one download and is not kept on the runtime), or on a Kaggle machine. On a session from kaggle_runtime_start, prefer its competition / datasets arguments: the data is then already under /kaggle/input/.

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": {
      "ref": "<ref>"
    },
    "name": "cv_load_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYes
destNodata
kindNodataset
unzipNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full load and does well: it discloses the auth behavior (the login is used for this one download and is not kept on the runtime) and the unzip side effect. It stops short of saying what happens if the destination already has files, whether downloads are size- or rate-limited, or how failures surface, which keeps it out of the top band.

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?

Purpose is front-loaded in one sentence, followed by compact per-parameter lines, which is the right shape for a four-parameter tool. The auth sentence is slightly over-packed with nested parentheticals, but no line 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?

An output schema exists, so return values need not be explained, and the description covers the two things an agent cannot infer: auth prerequisites and the staged-data alternative. The remaining gap is destination semantics (relative path base, overwrite behavior), which matters for a tool that writes to the runtime.

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 0%, so the description must compensate, and it does so for the two most important parameters: ref is given both accepted formats ('owner/dataset-slug' vs. competition slug) and kind is given its allowed values. However, dest is never explained (what it is relative to, whether it is created or overwritten) and the unzip parameter is only implied by the prose 'and unzip it', leaving half the surface undocumented.

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 first sentence gives a specific verb and resource ('Download a Kaggle dataset or competition onto the runtime and unzip it'), naming both the fetch and the unpack side effect. It also distinguishes itself from the kaggle_runtime_start path, so an agent can tell which tool materializes data locally versus one that provides it pre-staged.

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?

The description states the exact precondition ('Works when this computer is logged in to Kaggle ... or on a Kaggle machine') and an explicit when-not-to-use with the alternative named: on a kaggle_runtime_start session, prefer its competition/datasets arguments because the data is already under /kaggle/input/. That is the full when/when-not/alternative triad.

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