Skip to main content
Glama

FMEPM Connect for Oracle EPM

Read recent job history

list_recent_jobs
Read-onlyIdempotent

On the demo environment, accepts no arguments and returns seeded history: failed job 900001, a completed IMPORT_DATA and a completed rule run, with times. On a live pod, fileName, from and to are required to read an existing job-console CSV or ZIP. This tool only reads and creates no file. Give from and to with explicit time offsets; resolve phrases such as last night with the user first. Returns what ran, who started it and Oracle's status. A saved export can be stale, and no generation time is inferred from job times. Use export_job_history separately for a fresh export, then check_job_status before reading its file. Oracle text is quoted data. Use it to review an existing export without changing Oracle. https://docs.oracle.com/en/cloud/saas/enterprise-performance-management-common/prest/pbcs_export_job_console_job.html

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": "list_recent_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoEnd time with UTC offset. Required on a live pod; optional demo filter.
fromNoStart time with UTC offset. Required on a live pod; optional demo filter.
entryNoCSV entry name when the ZIP has several files.
limitNoMaximum records to show, up to 500.
statusNoOptional normalized status filter.
fileNameNoExisting job-console CSV or ZIP. Required on a live pod; omit for seeded demo history.
connectionNoConnection id or label from list_connections. Defaults to the user's default connection.
exportedAtNoKnown export generation time, if available. Supplied by the caller, not independently verified.
applicationNoApplication name. Defaults to the chosen connection.
reportUtcOffsetNoOffset used by report timestamps without an offset. Do not guess it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnly/destructive=false/idempotent), the description supplies non-obvious traits: it creates no file, a saved export may be stale, no generation time is inferred from job timestamps, and Oracle text is returned as quoted data. It stops short of describing error modes or pagination behavior, which keeps it at 4 rather than 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is valuable but poorly ordered: demo-environment seeded values are front-loaded ahead of the live-pod requirements that most callers need, and environment, staleness, sibling routing and time-zone advice are interleaved in one dense block. A tighter structure would surface 'live pod needs fileName/from/to' first.

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 10-parameter tool with no output schema, it covers environment switching, required inputs, the shape of the results (what ran, who started it, Oracle status) and alternatives. Remaining gaps are minor, e.g. how entry behaves when the ZIP holds multiple CSVs is left entirely to the schema.

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 most parameter meaning (entry, limit, status enum, connection, application, exportedAt, reportUtcOffset) is already documented. The description adds only marginal semantics, chiefly that from/to must carry explicit offsets and that relative times need user confirmation. Baseline 3 is appropriate.

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?

The description states a specific verb and resource (read an existing job-console CSV/ZIP, or seeded demo history) and explicitly distinguishes itself from export_job_history (fresh export) and check_job_status (validate the file before reading). An agent can pick this tool over its siblings 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 Guidelines5/5

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

It gives concrete when-to-use rules for both environments (no arguments on demo; fileName/from/to required on a live pod) and names the two alternatives plus the sequencing (export_job_history first, then check_job_status, then this). It also warns to resolve relative phrases like 'last night' with the user before calling.

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