Skip to main content
Glama

upload_dataset

Uploads a local directory as a private Kaggle dataset and returns a reference to pass to job submissions for reuse, with manual cleanup when done.

Instructions

Upload a local directory as a private Kaggle dataset to reuse across jobs.

Pass the returned ref in submit_job(datasets=[...]). Not deleted automatically;
use delete_dataset when done.

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": {
      "data_dir": "<data_dir>",
      "name": "<name>"
    },
    "name": "upload_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
data_dirYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden. It usefully reveals two non-obvious traits: the dataset is private and it is not deleted automatically. However, it says nothing about overwrite behavior on name collision, size or time limits, required permissions, or whether the upload is synchronous.

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?

Three short sentences, front-loaded with the core action, followed by downstream usage and cleanup in priority order. Every sentence adds distinct information with no restatement of the name or title.

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 and the description covers the key return value semantics (the ref is what you pass to submit_job), so explaining return shape is unnecessary. Lifecycle and consumption are covered; only edge-case behavior such as name collisions and permissions 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 description coverage is 0%, so the two bare parameters ('name', 'data_dir') rely entirely on the description. 'local directory' usefully clarifies that data_dir is a filesystem path and 'private Kaggle dataset' implies name is the dataset identifier, but no constraints on name format or uniqueness are given.

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?

States a specific verb and resource ('Upload a local directory as a private Kaggle dataset') plus the reason for doing so ('to reuse across jobs'). This clearly separates it from list_datasets and delete_dataset, which operate on existing datasets rather than creating new ones.

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?

Gives concrete downstream usage ('Pass the returned ref in submit_job(datasets=[...])') and routes cleanup to delete_dataset, so the agent knows both what to do with the result and how to undo the effect. It stops short of stating exclusions, e.g. what to do if a dataset with the same name already exists.

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