Skip to main content
Glama

Components Fields

components_fields
Destructive

Updates a Data Studio component's primary field lists and chart-local display names via native setters, with preview and validation; omit a role to keep it or pass [] to clear it.

Instructions

Replace primary field lists and chart-local display names with native setters.

Omit a role to keep it; [] requests clearing it, subject to native validation. Dimension-filter controls use native controlField/filterMetric bindings. Fields use names from datasource_get and metrics need explicit aggregation. Sources and source field definitions are unchanged. Set concept_name to an existing qt_* name from page_get to retain its ID and unmentioned metadata; otherwise creates a fresh chart-local concept. Independent sort dependencies are retained by Google, even when their fields are no longer visible. Preview returns the full updated components for review. Loaded static ungrouped components only; unsupported preset/UI dependencies are rejected. Formula selections use expression instead of name and run formula_validate before writing. Aggregate expressions require aggregation=7 (AUTO); row formulas need an explicit outer aggregation when used as metrics. Formula writes currently require identical draft/published datasource definitions. Other field roles, drill-down and datasource switching remain unsupported.

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": {
      "page_id": "<page_id>",
      "selections": "<selections>",
      "expected_page_fingerprint": "<expected_page_fingerprint>"
    },
    "name": "components_fields"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
page_idYes
report_idNo
selectionsYes
expected_page_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare a destructive write; the description adds what that destruction means: sources and source field definitions are unchanged, unmentioned roles are kept, independent sort dependencies survive, and preview returns the full updated components for review. It also discloses concept identity semantics (reusing a qt_* concept retains its ID and unmentioned metadata). Gaps remain on scope of the write per component and error/validation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense unbroken prose of roughly nine sentences mixing semantics, prerequisites, identity rules, and unsupported cases with no list or grouping. Almost every sentence carries information, but the ordering buries important invocation rules (validation ordering, draft/published constraint) in the middle.

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, destructive batch-mutation tool the description covers the major behaviors an agent needs: role omission/clearing, concept reuse, formula vs aggregate handling, and the supported component subset. The fingerprint/optimistic-concurrency parameter and dry_run default remain unstated, and an output schema exists so return values needn't be described.

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 0% schema description coverage the description must carry parameter meaning and largely does: name vs expression, required explicit aggregation, aggregation=7 meaning AUTO, concept_name sourcing from page_get, display_name as chart-local, omit-to-keep and []-to-clear semantics. It leaves payload-level fields such as page_id, report_id, expected_page_fingerprint, component_id and dry_run's relationship to 'Preview' unexplained.

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

Purpose4/5

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

Opens with a specific verb and resource: replacing primary field lists and chart-local display names via native setters. That distinguishes it from generic siblings like components_patch or components_filters, though the phrasing 'native setters' is jargon an agent must interpret.

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 real constraints on when this applies: 'Loaded static ungrouped components only; unsupported preset/UI dependencies are rejected', and formula selections must run formula_validate first with identical draft/published datasource definitions. It never explicitly contrasts with components_patch/components_filters, so routing between mutation siblings is still partly inferred.

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