Skip to main content
Glama

colab_transfer_download

Download files or directories from a Colab runtime to your local host, ensuring atomic transfers and retry on connection interruptions.

Instructions

Download atomically. Pre-submission connection failures retry once with the same still-valid lease/fingerprint; other interruptions require sync=true retry and hash verification.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
syncNoTrue skips local files with the same SHA-256; defaults to true.
sessionNoTracked session name. Null is allowed only when exactly one session exists.
max_filesNoHard file-count limit for a directory transfer.
overwriteNoWhen true, explicitly permit replacement of an existing destination.
chunk_sizeNoTransfer chunk size in bytes; 1-2,000,000. Defaults to 524,288.
local_pathYesPath on the MCP host, resolved under the host user's permissions.
compressionNoWire compression: auto uses gzip only when worthwhile; gzip forces it; none disables it.auto
lease_tokenNoOpaque operation-bound lease from colab_allocation_probe. Null performs a fresh probe.
remote_pathYesRuntime path confined to /content; relative paths resolve under /content.
max_total_bytesNoHard total transfer limit in bytes; checked before publication.
compression_min_bytesNoAuto mode only considers files at least this many content bytes; defaults to 1 MiB.
compression_min_savingsNoMinimum fractional wire-byte saving required by auto mode; defaults to 0.10.
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses atomicity, retry-once behavior with lease/fingerprint reuse, and the need for sync=true retry plus hash verification. This adds meaningful behavioral context beyond a simple 'download' label.

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?

Two concise sentences with no filler. Every phrase earns its place, and the key behavioral attributes (atomicity, retry semantics, sync requirement) are front-loaded.

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?

For a 12-parameter tool with no output schema and no annotations, the description is sparse. It covers failure-mode behavior but lacks general usage context, output/return expectations, and differentiation from sibling download tools. Adequate for a schema-heavy interface, but a clear gap remains.

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?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining how sync=true relates to retries and how lease_token participates in pre-submission retries, enriching parameter semantics beyond the schema's static descriptions.

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

Purpose3/5

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

The verb 'Download' is clear, but the description lacks a resource/scope (e.g., remote path, directory) and doesn't distinguish this from sibling colab_download. It mentions atomicity, which indicates behavior rather than purpose. It's not a tautology, but it's under-specified.

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?

Provides actionable retry guidance for pre-submission connection failures and other interruptions, which implies usage in failure scenarios. However, it does not state when to choose this tool over alternatives like colab_download or colab_fs_read, nor does it describe prerequisites.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/anluin/colab-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server