Skip to main content
Glama

get_workflow

Reports an integration's build lifecycle status and next steps. Set retrofit=true to derive state from an existing assembly when no aidlc-docs exists.

Instructions

Reports where an integration stands in its build lifecycle, and what to do next.

CALL THIS FIRST when picking up an integration you did not just scaffold — it answers "what is done, what is still a stub, and what should I do now?" without reading the XML.

THE LIFECYCLE (this MCP covers the first two phases):

  1. INCEPTION — plan_integration gathers the design and scaffolds the assembly + diagram, decomposed into sub-flows (the units of work).

  2. CONSTRUCTION — build ONE unit at a time: update_sub_flow to fill it in, then validate_assembly before moving to the next.

  3. OPERATIONS — deploy, tenant config, launch. NOT automated here: this server is local-only and never touches a tenant. The handoff checklist lives in aidlc-docs/plan.md.

State is read from /aidlc-docs/state.json, written by plan_integration and kept current by update_sub_flow and validate_assembly.

If a project has no aidlc-docs/ (it predates the convention, or was built by hand), call again with retrofit=true to derive one from the existing assembly. Retrofit records only what the assembly proves — sub-flows and which are still TODO stubs. It marks the design brief as unrecorded rather than inventing one.

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>"
    },
    "name": "get_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
retrofitNoGenerate aidlc-docs/ for a project that has none, by reading its existing assembly.xml
project_nameYesProject name, e.g. "INT999_Employee_Sync"

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

A4.8/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden, and it does: state is read from <project>/aidlc-docs/state.json, that file is written by plan_integration and kept current by update_sub_flow/validate_assembly, the server is local-only and never touches a tenant. It also discloses retrofit's limitation — it records only what the assembly proves and marks the design brief unrecorded rather than inventing one.

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 directive call-first instruction is front-loaded ahead of the supporting lifecycle detail, so the agent gets the actionable part immediately. The lifecycle enumeration is longer than strictly necessary but each phase carries routing value for the "what should I do now" answer.

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 status-reporting tool with no output schema, the description covers what the answer contains (what is done, what is still a stub, what to do next), where the state originates, how it stays current, and the retrofit path for legacy projects. Nothing an agent needs in order to call it correctly is missing.

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 both parameters are already documented; the baseline is 3. The description goes beyond the schema by explaining the semantic consequence of retrofit — when it is needed, what it derives from the existing assembly, and what it deliberately will not fabricate.

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 and resource: reports where an integration stands in its build lifecycle and what to do next. It explicitly separates itself from plan_integration (inception), update_sub_flow and validate_assembly (construction), so an agent can distinguish it from 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?

Gives an explicit trigger ("CALL THIS FIRST when picking up an integration you did not just scaffold") and names the sibling tools that cover the other lifecycle phases. It also states the precise condition for retrofit=true — a project with no aidlc-docs/ — plus the fallback when the precondition fails.

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