Skip to main content
Glama

plan_integration

Generate Workday Studio assembly and diagram skeleton files from gathered design decisions, scaffolding sub-flows, splitters, and auth before you build integration logic.

Instructions

⚠️ DO NOT CALL THIS TOOL without first gathering ALL design decisions from the user.

Design questions you MUST ask before calling:

  1. DATA SOURCE — How does data enter the integration? raas → Workday custom report (most common for scheduled/outbound) soap-get → Workday SOAP Get_* (when RAAS is not available) inbound-file → User uploads a file on the integration event webhook → Workday event listener fires (listener-service) external-rest → Fetch data from a third-party REST API

  2. DATA DESTINATION — Where does processed data go? workday-soap-write → Workday SOAP Put_*/Change_*/Hire_* etc. workday-rest-write → Workday REST custom objects PUT/POST/DELETE external-rest → POST/PATCH to a third-party API file-delivery → Output file delivered on the integration event email-only → Send email notification (no system update)

  3. TRIGGER — What launches this integration? scheduled → Workday scheduler (daily, hourly, etc.) event-driven → Workday business event (hire, terminate, etc.) launch-params-manual → Manually launched, optional filter params inbound-file → Triggered by file upload on the integration event

  4. RECORD VOLUME — How many records does the integration process? single → Always exactly 1 record (no splitter needed) small → Under 100 records (xpath-splitter loads all into memory) large → Over 100 records (MUST use xml-stream-splitter for streaming)

  5. EXTERNAL AUTH — What auth does the external system require? none → No external system involved oauth2 → OAuth2 token refresh flow (adds GetToken sub-flow) basic → Username + password (Base64 encoded) api-key → Static API key

  6. ERROR HANDLING: integration-messages → Log to Workday event log (always minimum) email-notification → Send failure email (adds Email sub-flow) rethrow → Stop integration and propagate the error

  7. RAAS REPORTS (if data_source = raas or multiple): For each report: alias name, what data it returns, any filter params. Filter param syntax: "Worker!WID" for object refs, "Effective_Date" for text, "format=simplexml" to strip wd: namespaces from response. Example: alias="INT145_Get_Workers", filters=["Worker!WID", "format=simplexml"]

  8. SOAP OPERATIONS (if soap-get or workday-soap-write): For each: application (e.g. Human_Resources), operation (e.g. Get_Workers), version.

  9. INTEGRATION ATTRIBUTES: Any credentials or config stored in Workday? (API keys, URLs, OAuth credentials) Note: oauth2/basic/api-key auth types auto-generate the standard attributes.

  10. CONDITIONAL LOGIC: Any routing decisions? e.g. "employee vs contractor", "new hire vs rehire", "active only"

Once you have all answers, call with project_name + sub_flows + design_brief. The tool writes assembly.xml + assembly-diagram.xml with correct declarations pre-populated.

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": {
      "project_name": "<project_name>",
      "sub_flows": "<sub_flows>",
      "design_brief": "<design_brief>"
    },
    "name": "plan_integration"
  }
}

Input Schema

NameRequiredDescriptionDefault
sub_flowsYesOrdered list of sub-flows. Order = execution order in the main flow chain.
design_briefYes
project_nameYesExisting project name (e.g. "INT145_My_Integration"). Must already exist in the workspace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does disclose the side effect (writes assembly.xml + assembly-diagram.xml) and that project_name 'Must already exist in the workspace.' It does not say whether an existing assembly.xml is overwritten, what is returned, or what happens if the sub-flow list is invalid for the chosen design — meaningful gaps for a file-generating mutation tool.

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 numbered structure is scannable and suits a complex planning tool, but the document is long and largely duplicates enum definitions already present in the nested schema. The front-loaded 'DO NOT CALL' warning occupies the position where the purpose statement should be, forcing a full read before the agent knows what it is being warned about.

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 three-parameter, deeply nested generator with no output schema, the description covers the design inputs thoroughly and names the produced artifacts. What is missing is downstream context — overwrite behavior on re-run and how this relates to the validate/add-step siblings an agent would naturally chain afterward.

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 coverage is 67% with rich per-field descriptions, so the baseline is 3. Much of the ten-item checklist restates enum semantics already documented in design_brief (raas=Workday custom report, large=MUST use xml-stream-splitter, oauth2=token refresh flow), adding little. The genuinely additive bits are the RAAS filter-param syntax example and the alias naming convention, which are useful but partial.

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?

The concrete effect is stated but only at the very end: 'The tool writes assembly.xml + assembly-diagram.xml with correct declarations pre-populated,' which distinguishes it from write_integration_file or add_assembly_step. The opening line is a warning block rather than a purpose statement, so the agent has to read to the bottom to learn what the tool builds. The specific named artifacts make it clear enough once found.

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?

Preconditions are unusually explicit: 'DO NOT CALL THIS TOOL without first gathering ALL design decisions,' followed by ten enumerated decision areas and the closing 'Once you have all answers, call with...'. No sibling tool is named as an alternative (e.g. validate_assembly or add_assembly_step for post-generation steps), so routing among siblings is left to inference.

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