Skip to main content
Glama

FMEPM Connect for Oracle EPM

Check a total

reconcile_total
Read-onlyIdempotent

Reads a parent and its exact direct children from Oracle at one point of view and compares the total using outline order, consolidation operators and account time balance. Computed amounts are labeled separately from Oracle's own total. Formulas, label-only parents, incomplete children or unavailable calculation metadata return not comparable. Service Administrator access is needed for Oracle member properties. Use it before presenting a total computed from children.

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": {
      "cube": "<cube>",
      "dimension": "<dimension>",
      "parent": "<parent>",
      "members": "<members>",
      "pov": "<pov>"
    },
    "name": "reconcile_total"
  }
}

Input Schema

NameRequiredDescriptionDefault
povYesExact members for the other dimensions. Organization defaults fill missing choices; otherwise name each member. No remembered point of view.
cubeYesCube to read.
parentYesExact parent member.
membersYesAll direct children, including ignored members. Outline order comes from Oracle.
dimensionYesThe dimension whose parent is checked.
toleranceNoAbsolute tolerance for the comparison, in the same units as the cells.
connectionNoConnection id or label from list_connections. Defaults to the user's default connection.
applicationNoApplication; defaults to the connection.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already signal a safe read (readOnlyHint, idempotent, non-destructive), and the description adds meaningful context beyond them: the Service Administrator access requirement, the fact that computed amounts are labeled separately from Oracle's own total, and the specific cases yielding 'not comparable'. This is rich behavioral disclosure, though the return shape is only partially described.

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?

Four dense sentences, front-loaded with what the tool does. The permission note and edge-case list each earn their place. Slightly packed but no filler.

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 an 8-parameter tool with a nested pov object and no output schema, the description does the heavy lifting: it covers purpose, auth, edge cases, and return labeling. A fuller account of the return structure would push it higher, but it is largely complete.

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?

Schema description coverage is 100%, so each parameter is already documented. The description adds modest meaning (outline order for members, point-of-view reading, calculation metadata) but nothing about the specific parameters beyond what the schema states. Baseline 3 applies.

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 action (reads a parent and its direct children, compares the total) on a specific resource (Oracle) at a point of view. Clear enough to distinguish from siblings like explain_variance or recompute_insights, though it doesn't name an alternative. The verb+resource pairing is unambiguous.

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?

Explicitly says 'Use it before presenting a total computed from children,' giving clear when-to-use guidance. It also enumerates when the tool returns 'not comparable' (formulas, label-only parents, incomplete children, missing metadata), which is a useful negative condition. No named alternatives, keeping it from a 5.

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