Skip to main content
Glama

Datasource Fields Edit Metadata

datasource_fields_edit_metadata
Destructive

Edit datasource field labels, descriptions, types, aggregation, and visibility while preserving unknown metadata and safely checking formula and report dependencies before changes.

Instructions

Edit field labels, descriptions, types/semantics, aggregation or visibility.

Works for physical and calculated fields while retaining identity and all unspecified/unknown metadata. data_type and semantic_config must be supplied together because changing one alone creates inconsistent field semantics. Type, aggregation, and disabling changes inspect datasource formula dependents and full-report saved references; used fields require allow_in_use=true. Shared sources additionally require allow_shared_source=true and preview reports their external impact scope. Matching draft/published and source fingerprint are required. The report fingerprint is guarded through publication; full-draft publish is journaled, read back, and reversible 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": {
      "datasource_id": "<datasource_id>",
      "changes": "<changes>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "datasource_fields_edit_metadata"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
dry_runNo
report_idNo
allow_in_useNo
datasource_idYes
allow_shared_sourceNo
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
Behavior5/5

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

Annotations already flag this as a non-readonly, destructive mutation, and the description goes well beyond them: dependent-formula and full-report saved-reference inspection, external impact previews for shared sources, fingerprint guarding through publication, and journaled/read-back publication that is reversible via operation_restore. That is exactly the kind of consequence-and-recovery context an agent needs before running a destructive edit.

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?

The purpose is front-loaded correctly and every sentence carries a constraint, so there is little filler. The prose is dense and fragmentary, though, with clipped clauses ('Matching draft/published and source fingerprint are required') and a closing pair of sentences about journaling that are opaque rather than informative.

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?

An output schema exists, so return values need not be described, and the description covers the destructive-operation lifecycle including dependency checks, preview scope, and rollback. The remaining gap is the unstated dry_run default, which materially changes what a call does and is not recoverable from the undescribed 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 0% schema description coverage the description must carry the load, and it covers most of it: it maps the editable attributes in 'changes', explains the data_type/semantic_config pairing rule, the allow_in_use and allow_shared_source gates, and that expected_fingerprint must match draft/published and source state. However, dry_run (which defaults to true, meaning edits are previewed unless flipped) and report_id are never explained, which is a meaningful omission for a 7-parameter mutation.

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?

The first sentence names a specific verb (edit) and enumerates the exact metadata it mutates (labels, descriptions, types/semantics, aggregation, visibility). The clause 'retaining identity' implicitly distinguishes it from the sibling datasource_fields_rename, but no sibling is named explicitly, so the differentiation is left to inference.

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 concrete preconditions that select or block usage: used fields require allow_in_use=true, shared sources require allow_shared_source=true, and data_type/semantic_config must be supplied together. It never states when to reach for datasource_fields_rename or datasource_calculated_fields_edit instead, so it is strong on constraints but silent on alternatives.

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