Skip to main content
Glama

Datasource Create Bigquery

datasource_create_bigquery

Create a BigQuery datasource from a table or custom SQL query, optionally attaching it to a report or validating fields with a dry run.

Instructions

Create a BigQuery datasource from a table or a custom query (Add data > BigQuery).

source: {project_id, dataset_id, table_id} for a table, or {project_id (billing project), sql, legacy_sql?, date_range_params?, viewer_email_param?} for a custom query (the params enable @DS_START_DATE/@DS_END_DATE and @DS_USER_EMAIL); optional name, billing_project_id. With a report (active or report_id) and attach_to_report it is embedded in that report and named in its datasourceAlias, ready for components; otherwise a reusable datasource owned by the account. dry_run reads the connector fields (validating access/SQL) without creating anything. Field names in the result are what components_create and formulas use.

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": {
      "source": "<source>"
    },
    "name": "datasource_create_bigquery"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYesA table (project_id + dataset_id + table_id) or a custom query (sql).
dry_runNo
report_idNo
attach_to_reportNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the important behavioral detail that dry_run (default true) validates access/SQL without creating anything, and that creation either embeds into a report under datasourceAlias or produces an account-owned reusable datasource. It does not cover permissions or rate limits, so 4 rather than 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?

Front-loaded with the core action, then structured by mode (source shape, optional fields, report vs. reusable, dry_run, result usage). It is dense and parenthetical, verging on packed, but nearly every clause carries actionable information.

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 nested-object mutation tool with several defaulted booleans, the description covers the two input modes, the dry-run path, the attachment semantics, and how results feed later component/formula creation. An output schema exists, so return-value detail is rightly omitted; only permission/auth prerequisites remain unstated.

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 only 25%, but the description compensates well by explaining the source object shapes, what billing_project_id means, what date_range_params and viewer_email_param enable (@DS_START_DATE/@DS_END_DATE, @DS_USER_EMAIL), and the consequence of attach_to_report. It adds the non-obvious note that field names in the result drive components_create and formulas.

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 and resource ('Create a BigQuery datasource') and immediately enumerates the two supported shapes (table vs. custom query), plus the UI path 'Add data > BigQuery' for disambiguation. It also distinguishes its own report-embedding mode from the separate re-attach behavior an agent would otherwise confuse with datasource_add_to_report.

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 clear selection context: table shape versus custom-query shape, and report-embedded (with active report/report_id and attach_to_report) versus account-owned reusable datasource. It does not name explicit alternatives or when-not-to-use conditions (e.g., use bigquery_browse to discover table ids), so it falls short of a 5.

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

Deploy Server

Other Tools