Skip to main content
Glama

Create Datasets Tool

create-datasets

Create one or many custom datasets in a project. Pass user columns only; catalog system columns are added automatically. fact_id and dim_id are added only when a column with that name is included. The catalog supplies their definition. is_primary_key comes from the request and is allowed only on upsert. write_mode is upsert or append_only. versioned is accepted and reported as append_only. Character length comes from value_type, not a free max length. If any table fails validation, nothing in the call is created.

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": {
      "project_id": "<project_id>",
      "tables": "<tables>"
    },
    "name": "create-datasets"
  }
}

Input Schema

NameRequiredDescriptionDefault
spaceNoSpace slug. Required when the token is bound to more than one space. Omit it when the token has one space.
tablesYesOne object creates one dataset. Several objects are created together, or not at all if any object is invalid.
project_idYesProject that will own the datasets. It must belong to the token space.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With annotations empty the description carries the full burden, and it discloses real behavior: system columns are auto-added by the catalog, versioned is silently coerced to append_only, and the call is atomic ('nothing in the call is created' on any validation failure). It omits what the call returns (dataset identifiers) and any permission requirements, which keeps it short of a 5.

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 and the remaining sentences are terse rule statements with no filler. It loses a point for restating schema text nearly verbatim (the columns description repeats the fact_id/dim_id and is_primary_key sentences almost word for word).

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?

For a mutation tool with no annotations and no output schema, the definition covers atomicity, auto-added system columns, and per-field constraints well. The main residual gap is the return value and any failure-detail shape after a rejected validation, which an agent would want before retrying.

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 description coverage is already 100%, so the baseline is 3; the description earns above that by adding cross-field meaning the schema does not — character length derives from value_type rather than a free max-length field, and is_primary_key is request-supplied and only legal on upsert. Nesting of tables/columns is also clarified as one-object-per-dataset.

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?

Opens with a specific verb, resource, and cardinality: 'Create one or many custom datasets in a project.' That clearly separates it from the read-oriented siblings such as list-datasets, get-dataset-metadata, and get-dataset-sample without needing to name them.

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?

The description implies the create path but never states when to use this versus the list/get siblings, or any prerequisites (permissions, project membership beyond 'must belong to the token space'). What it does supply are in-call rules (write_mode values, is_primary_key only on upsert) rather than use-case routing.

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.

Resources