Skip to main content
Glama

Datasource Calculated Fields Delete

datasource_calculated_fields_delete
Destructive

Delete unused user-created calculated fields from an attached datasource after fail-closed dependency and report-reference checks; previews by default and journals reversible, read-back-verified publication.

Instructions

Delete unused user-created calculated fields from an attached datasource.

Fail-closed safety checks cover the native datasource formula dependency graph and identifier-token references across the full saved report, all pages and resources. Ownerless report matches are blockers; matches explicitly scoped to another datasource are informational. A batch may delete fields that depend on each other, but any dependent outside the batch blocks it. Requires complete formula parsing, matching draft/published, datasource fingerprint, and an unchanged report through the final preflight. Preview by default; publication 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>",
      "field_names": "<field_names>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "datasource_calculated_fields_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
report_idNo
field_namesYes
datasource_idYes
allow_shared_sourceNo
expected_fingerprintYes
allow_unscanned_shared_consumersNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only declare destructive=true; the description goes far beyond them, disclosing fail-closed dependency-graph and identifier-token checks, the ownerless-vs-scoped match distinction, intra-batch dependency rules, parse/fingerprint/draft-published preconditions, dry-run default, and journaled read-back rollback. For a destructive mutation this is exactly the behavioral context an agent needs.

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?

The purpose sentence is front-loaded and every subsequent sentence carries substantive safety information, with no filler. Some clauses are densely packed with jargon ("matching draft/published, datasource fingerprint") and could be broken out for scannability, but nothing is wasted.

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?

The output schema means return values need not be explained, and the destructive safety model is unusually well covered. However, for a 7-parameter destructive tool the two allow_* override flags are invisible to the agent, which is a meaningful gap in a definition that otherwise leans hard on fail-closed guarantees.

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

Parameters2/5

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

Schema description coverage is 0% across 7 parameters, so the description carries the full burden, yet it names no parameter. It hints at expected_fingerprint ("datasource fingerprint") and the dry_run default ("preview by default"), but allow_shared_source and allow_unscanned_shared_consumers are safety-bypass flags left entirely unexplained, as are report_id scoping and field_names batch semantics.

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 plus a scope qualifier: "Delete unused user-created calculated fields from an attached datasource." This clearly separates it from the create/edit siblings of the same resource and tells an agent exactly what class of object is affected.

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?

Usage is implied rather than stated: the tool deletes, it previews by default, and publication is reversible via operation_restore, which gestures at a safe workflow. There is no explicit when-to-use/when-not-to-use rule (e.g. prefer edit for renaming, prefer this only for fields with no consumers), so the agent has to infer routing from the safety narrative.

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