Skip to main content
Glama

Datasource Fields Rename

datasource_fields_rename
Destructive

Rename datasource field labels while preserving internal IDs and other definitions. Use fingerprint checks to prevent conflicts and preview changes with a dry run.

Instructions

Rename datasource field labels, preserving internal IDs and all other definitions.

Shared sources require allow_shared_source=true and report external impact. Requires matching draft/published to avoid publishing human drafts. Get fingerprint from datasource_get. Publishes full draft, independently reads both states, journals before/after for operation_restore. No automatic retry. This API has no characterized server CAS; preflight cannot lock out other clients.

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_rename"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
dry_runNo
report_idNo
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?

Well beyond the destructiveHint=true annotation, it discloses that the call publishes the full draft, journals before/after for operation_restore, does not auto-retry, and that there is no server-side CAS so preflight cannot lock out other clients. These are exactly the risk and concurrency facts an agent needs before a destructive write.

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 and its invariant lead, followed by preconditions then operational caveats, with no filler sentences. The telegraphic style ('Requires matching draft/published', 'journals before/after') is dense but every clause carries 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 destructive, non-CAS write with six parameters the description covers the risky behavior, the shared-source gate, the fingerprint prerequisite, and recovery via operation_restore; an output schema exists so return values need no explanation. The remaining gap is the undocumented `changes` payload and report_id, which the empty schema descriptions leave unresolved.

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

Parameters3/5

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

With 0% schema description coverage the description must carry all parameter meaning, and it only explains allow_shared_source and expected_fingerprint. Nothing is said about the shape of `changes` (field_name/output_name mapping), the semantics of dry_run defaulting to true, or what report_id does.

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?

States a specific verb and resource ('Rename datasource field labels') plus the key invariant 'preserving internal IDs and all other definitions', which implicitly separates it from datasource_rename and datasource_fields_edit_metadata. It stops short of naming a sibling explicitly, so routing still requires the agent to infer the boundary.

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: shared sources need allow_shared_source=true, draft/published states must match, and the fingerprint must come from datasource_get. It states consequences ('report external impact', 'avoid publishing human drafts') but never says when to prefer a sibling such as datasource_fields_edit_metadata over this tool.

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