Skip to main content
Glama

datasets_upload

Get your data in. Pass data as an array of row objects to create the dataset immediately and get a dataset_ref ready for path_resolver; omit it to get an upload link for a file only the user can reach. Add replace_ref (uuid://ID:KEY) with data to REFRESH an existing dataset in place; schedules and tools holding that reference read the new data on their next run.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "datasets_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoRows as an array of flat objects, creates the dataset in one call
expires_inNoNot used: an upload link always lasts 20 minutes (see expires_at)
replace_refNouuid://ID:KEY of an existing dataset to overwrite in place with `data` (the push/refresh mode); the previous rows are deleted, no copy is kept

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / expires_in / default
      Removed value: -300
    • changedInput schema / properties / expires_in / description
      Previous value: -"Token expiration in seconds"New value: +"Not used: an upload link always lasts 20 minutes (see expires_at)"
    • changedInput schema / properties / replace_ref / description
      Previous value: -"uuid://ID:KEY of an existing dataset to overwrite in place with `data` (the push/refresh mode)"New value: +"uuid://ID:KEY of an existing dataset to overwrite in place with `data` (the push/refresh mode); the previous rows are deleted, no copy is kept"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations: it discloses that an upload link is scoped to a file 'only the user can reach', that refresh deletes previous rows with no copy kept, and that schedules and tools holding the ref will read new data on their next run. That downstream-impact disclosure is exactly the context annotations cannot carry. One tension: `destructiveHint: false` understates the refresh path's row deletion, so the description, not the annotation, is the accurate source of truth for an agent.

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?

Very information-dense across three sentences with conditionals front-loaded ('Pass `data`...', 'Add replace_ref...'), and each sentence carries distinct mode information. The 'Get your data in.' opener is filler, and the long middle sentence packs two modes together, slightly reducing scanability.

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?

No output schema exists, and the description compensates by describing both possible returns (an immediate dataset_ref vs. an upload link). All three parameters are addressed and the refresh side effects are covered. The only gap is upload-link mechanics such as the 20-minute expiry, which live solely in the schema.

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 100% schema coverage the baseline is 3, and the description earns more by documenting the combinatorial semantics the schema cannot: `data` alone means create, `data` + `replace_ref` means refresh-in-place, absence of `data` means upload link. It also gives the `replace_ref` format inline. `expires_in` is left to the schema, which is acceptable since the schema marks it as unused.

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?

Names a specific resource (dataset) and three distinct actions — create immediately from `data`, obtain an upload link, or refresh an existing dataset in place via `replace_ref`. The output artifact (`dataset_ref` consumable by path_resolver) is stated, so an agent can tell what it gets and how it differs from siblings like datasets_list or path_resolver.

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?

Mode selection is spelled out explicitly: pass `data` to create, omit it to get an upload link, add `replace_ref` alongside `data` to refresh. That covers the when-to-use cases well and points at path_resolver as the downstream consumer, but there is no explicit when-not guidance (e.g., when to list/inspect with datasets_list instead) or prerequisite/permission conditions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.