Skip to main content
Glama

Compile a POM suite to runnable flows

qa_flow_compile
Idempotent

Compile a POM suite from .swipium/suites into runnable, validated flows under .swipium/flows, so mobile QA flows are ready to execute on emulators or simulators.

Instructions

Compile a POM suite on disk (.swipium/suites/.yaml) into runnable flows under .swipium/flows/ and validate them. No session needed; qa_generate target:"suite" already compiles what it generates.

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": "qa_flow_compile"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoOverwrite .swipium/flows/<slug>.yaml even when it was edited by hand since the last compile (default: keep it, write <slug>.yaml.new).
suiteNoSuite file relative to .swipium/ (default suites/smoke.yaml).
sessionIdNo
projectRootNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and idempotentHint=true; the description adds that output lands in .swipium/flows/, that compilation includes validation, and that no session is required. That is genuine context beyond the annotations. The one omission is that the description doesn't itself flag the hand-edited-file hazard that force governs, leaving that entirely to the schema text.

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

Conciseness5/5

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

Two sentences, zero filler: the first states the transformation and its paths, the second states the precondition and the alternative. The most decision-relevant fact (what it produces and where) is front-loaded.

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 file-writing compile tool with no output schema, the definition covers input path, output path, validation, session requirements, and the redundant-work case. Only the return value and failure behavior are left unstated, which is a minor gap given how mechanical the operation is.

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 only 50%, so the description has to compensate, and it partly does: it pins the suite file location to .swipium/suites/<suite>.yaml and states "No session needed," which effectively explains why the sessionId parameter is optional. projectRoot remains unexplained beyond its schema stub.

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?

"Compile a POM suite on disk (.swipium/suites/<suite>.yaml) into runnable flows under .swipium/flows/ and validate them" gives a specific verb pair, an explicit input path, an explicit output path, and the extra validation step. It also names the sibling (qa_generate target:"suite") that already does this implicitly, so an agent can distinguish the two without opening either 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?

It supplies a real when-not rule: if qa_generate with target:"suite" already produced flows, this compile step is redundant. It also removes a common blocker by stating "No session needed." It does not say when to prefer the adjacent qa_flow_check or qa_flow_repair, but the guidance it does give is concrete rather than implied.

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