Skip to main content
Glama

hf_push_run

Upload a training run's checkpoints, metrics, logs, and scripts from a remote GPU runtime to Hugging Face Hub in the background, avoiding local transfers; call again to check progress.

Instructions

Upload a run's folder (checkpoints, metrics, log, script) from the runtime to the Hub.

The upload goes straight from the remote machine, in the background, so large checkpoints never pass through this computer. Call it again to check progress. It uses this computer's Hugging Face login for that one upload; the token is not kept on the runtime.

repo_id: defaults to "/<run_name>".

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": {
      "run_name": "<run_name>"
    },
    "name": "hf_push_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
privateNo
repo_idNo
run_nameYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that the transfer is backgrounded and goes directly from the remote machine (large checkpoints bypass the local computer), that the call is meant to be repeated for progress, and that it uses the local Hugging Face login with the token not persisted on the runtime. It does not cover overwrite/idempotency behavior or whether a missing repo gets created.

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?

The action is front-loaded in the first sentence, followed by behavior (background, direct-from-remote), polling guidance, auth notes, and the one parameter default. Every sentence adds information an agent needs; nothing is redundant.

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

Completeness3/5

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

An output schema exists, so return-value explanation is unnecessary, and the async/remote-transfer model is clearly conveyed. Gaps remain around the 'private' parameter, whether an existing repo is overwritten, and failure modes — all material for a write operation with no annotations.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must explain all three parameters. It only documents repo_id's default format ('<your username>/<run_name>'); run_name is only implied, and the 'private' flag — which plausibly controls repo visibility/creation — is never explained at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: it uploads a run's folder (checkpoints, metrics, log, script) from the runtime to the Hub. The contents list makes it distinguishable from a generic file upload, but it never explicitly contrasts itself with siblings such as hf_upload or hf_download.

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

Usage Guidelines3/5

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

It gives one genuinely useful usage rule — call it again to check progress — which tells the agent this is a resumable/pollable operation. However, there is no guidance on when to prefer this over hf_upload, nor on prerequisites (e.g. does the run need to be finished, must the repo exist first).

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