Skip to main content
Glama

FMEPM Connect for Oracle EPM

Plan a development change

plan_change
Destructive

Saves one exact development plan, connection, application, before and after metadata, and checksums for review. It does not apply a change. Admin profile and enabled Development changes are required. Live existing substitution variables support before-value backup, apply, readback, promotion and undo. Live members support add, checked property edits and moves with admin-configured metadata jobs and cube refresh. Live rename and deletion refuse; undo cannot delete an added member. Forms, rules, scripts, maps, lists and flows remain demo rehearsals. Unsupported live paths are blocked. No rule script or financial calculation is executed by that rehearsal. Use it to plan first, then review the record before a separate run_change confirmation. For a write, I require a preview first, then confirm: true and its confirmationToken. The token lasts ten minutes and works once.

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": {
      "application": "<application>",
      "operation": "<operation>"
    },
    "name": "plan_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoSet true after the user has approved the previewed change
operationYesOne exact change, without passwords, tokens or financial cell values.
connectionNoConnection id or label from list_connections. Defaults to the user's default connection.
applicationYesExact application name, bound to the plan and checked by policy.
confirmationTokenNoSingle-use token from this exact preview. Send it with confirm: true after the user approves. It expires after ten minutes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing prerequisites, which live paths are supported versus refused (rename and deletion refuse; undo cannot delete an added member), that non-live artifacts stay rehearsal-only, and that the confirmation token is single-use and expires in ten minutes. The one wrinkle is a mild tension with destructiveHint=true while the text insists it "does not apply a change" — defensible as the plan recording a destructive change, but not reconciled explicitly.

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?

Purpose and the not-applied caveat are front-loaded, and the capability/refusal inventory genuinely earns its space by telling the agent which plans will fail. It is dense and slightly awkward in places ("Live existing substitution variables support before-value backup, apply, readback, promotion and undo"), and the first-person "I require a preview first" is a register break, but there is little true redundancy.

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, deeply nested, five-parameter tool with no output schema, the description covers prerequisites, live-vs-rehearsal limits, and the confirm/token lifecycle. What it leaves implicit is the shape of what comes back — that the preview yields the plan record and confirmationToken — which the agent must infer from the token sentence.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter workflow meaning the schema cannot express: preview must precede confirm, confirm requires confirmationToken from that exact preview, and the token is single-use with a ten-minute life. It also explains that live member changes require admin-configured jobs and cube refresh approval, which ties refreshCube to the operation.

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 — saves one exact development plan (connection, application, before/after metadata, checksums) — and immediately negates the wrong reading: "It does not apply a change." That contrast with the sibling run_change is explicit, so an agent can distinguish the two without inspecting either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States the workflow directly: "Use it to plan first, then review the record before a separate run_change confirmation," naming the alternative tool and the ordering condition that selects it. It also gates usage on prerequisites (admin profile, enabled Development changes) and describes the confirm/token handshake, leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources