Skip to main content
Glama

Report Variables Write

report_variables_write
Destructive

Create, replace, or delete Google Data Studio report variables with previewed, conflict-checked writes that can be restored.

Instructions

Create, replace or delete report variables (Manage variables). Each upsert is {parameter_key, parameter}: parameter is the wire shape report_variables_list returns (parametersModifiedByRoles roles 1 and 5 with dataType, defaultValue, options, optional parameterQueryConfig; parameterDisplayConfiguration.displayName). Deleting a variable still bound by Control visibility is refused. Journalled, verified, restorable with operation_restore.

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": {
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "report_variables_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
deletesNo
dry_runNo
upsertsNo
report_idNo
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description correctly reinforces that with the refusal rule for bound variables plus journalled/verified/restorable semantics, which genuinely adds context beyond the annotations. It stops short of explaining the optimistic-concurrency guard (expected_fingerprint) or the dry-run default, both central behaviors for a destructive tool.

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?

Dense and front-loaded: purpose first, then upsert shape, then the refusal rule, then reversibility. Parenthetical-heavy jargon (roles 1 and 5, parameterQueryConfig) costs some readability but every sentence carries information.

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?

With a destructive write tool, 0% schema description coverage, and a required expected_fingerprint plus a dry_run that defaults to true, the description leaves two decision-critical parameters unexplained. The payload shape and safety/reversibility story are covered, and an output schema exists so return values need no explanation, but the concurrency and dry-run gaps keep it from being complete.

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

Parameters5/5

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

Placeholder.

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?

States a specific verb set (create, replace, delete) and resource (report variables), and anchors the payload shape to what report_variables_list returns, which separates it from the read-oriented sibling. An agent can tell this is the write counterpart without opening the schema.

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?

Gives two useful usage facts: deletion is refused when a variable is bound by Control visibility, and changes can be undone via operation_restore. But it never tells the agent when to write versus read via report_variables_list, and critically omits that dry_run defaults to true, so a caller may believe it wrote when nothing was applied.

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