FMEPM Connect for Oracle EPM

Read Oracle audit changes

read_audit_changes

Destructive

Exports Oracle's audit after a preview and confirm:true, waits for the job, downloads its ZIP and returns the audit CSV rows: when, who, the intersection Oracle supplied, old and new values, audit type, and change counts by person and account. Use it for who changed what and when. The export creates a file in Oracle; no value is written to a cube. Account, member and user filters are applied locally. Unparsed intersections keep Oracle's full Details text and are marked unparsed. The demo has no Oracle audit; remembered_results can compare a previous read instead. Oracle's data audit covers edits through forms. Calculations, data maps and direct Essbase loads leave no cell-change records. A data load may not appear, depending on the audit settings. An empty export does not show whether Data auditing is enabled. https://docs.oracle.com/en/cloud/saas/enterprise-performance-management-common/prest/pbcs_export_audit_records.html 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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_audit_changes"
  }
}

Input Schema

Name	Required	Description
`to`	No	UTC date or date and time with an explicit offset. An explicit range takes precedence over days and cannot exceed 90 days or include future dates.
`days`	No	Days to review, from 1 to 90. Defaults to 30; an explicit from/to range takes precedence.
`from`	No	UTC date or date and time with an explicit offset. An explicit range takes precedence over days and cannot exceed 90 days or include future dates.
`user`	No	Optional exact Oracle user id or name. Not a group name.
`account`	No	Optional exact Account member filter.
`confirm`	No	Set true after the user has approved the previewed change
`members`	No	Optional exact members by any dimension. Several members in a dimension mean any of those members; all dimensions must match.
`connection`	No	Connection id or label from list_connections. Defaults to the user's default connection.
`application`	No	Application name. Defaults to the selected connection's application.
`confirmationToken`	No	Single-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.

AddedOct 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: explains that the export creates a file in Oracle (justifying readOnlyHint=false / destructiveHint=true) while writing no cube values, that filtering (account/member/user) happens locally, that unparsed intersections are flagged and keep Oracle's full Details text, and that the two-step preview requires confirm:true plus a single-use token that expires in ten minutes. This is exactly the behavioral context annotations cannot convey.

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 return shape are front-loaded in the first sentence, and most sentences carry distinct, non-redundant information. It is long and dense with caveats, and the docs link plus the preview/token rules at the tail could be tightened, but no sentence is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with nested member objects and no output schema, the description supplies the missing return contract (CSV columns, counts by person and account, unparsed marking) and the full preview-confirm-token workflow. An agent has everything needed to invoke it safely and interpret the result.

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 100% schema coverage the baseline is 3; the description earns above that by disclosing that account, member and user filters are applied locally rather than server-side, and by explaining the unparsed-intersection handling. It does not add new detail on the date range, days, or connection defaults, which the schema already covers.

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?

States a specific verb chain and resource: exports Oracle's audit, waits for the job, downloads the ZIP, returns CSV rows with named fields (when, who, intersections, old/new values, audit type, change counts). An agent can distinguish it from list_changes, read_intersections and remembered_results without opening any schema.

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?

'Use it for who changed what and when' gives clear usage context, and the description routes the demo case to remembered_results as an alternative. It also lists when results will be absent (calculations, data maps, direct Essbase loads, audit-setting dependence), but it never explicitly contrasts with the closest sibling list_changes, so the when-not guidance is coverage-oriented rather than alternative-oriented.

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

All FMEPM Connect for Oracle EPM tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?