Skip to main content
Glama
Java Project Runner MCP

Java Project Runner MCP

project_start

Starts a configured Java project’s JAR as a detached process, building with Maven when needed; optionally force a rebuild or skip the build if an existing JAR is ready.

Instructions

Start the configured JAR (detached process group). Builds with Maven unless the JAR is fresh or skipBuild is set; use rebuild to force package.

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": {
      "projectId": "<projectId>"
    },
    "name": "project_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileNo
rebuildNoForce Maven package before start
projectIdYes
skipBuildNoSkip Maven; require an existing resolvable JAR

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does add genuine behavior: a Maven build fires implicitly unless the JAR is fresh or skipBuild is set, and the process is detached. Undisclosed gaps remain material for a mutation/launch tool — behavior when already running, whether it blocks until healthy, and what is returned (PID? status?).

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 compact sentences; the core action is front-loaded, followed by the build logic that would otherwise surprise the caller. No filler.

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

Completeness3/5

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

Covers the build/skipBuild decision adequately for a 4-parameter tool with no output schema, but leaves two of four parameters (projectId, profile) undefined in both schema and description, and says nothing about return value or behavior when the process is already running.

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?

No parameter is described beyond the schema; skipBuild is documented in the schema, rebuild too — the description just restates them and, crucially, says how they interact (skipBuild overrides the default build; rebuild forces it). That interaction is real added meaning, though profile and projectId remain unexplained — a documented gap at 50% coverage.

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?

States a specific verb and resource: 'Start the configured JAR', with the parenthetical clarifying it runs as a detached process group. That distinguishes it from project_build (build only) and project_restart, though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

It gives a real decision rule between the default build path and 'rebuild to force package', and mentions skipBuild as an alternate mode. But there is no guidance on when to choose project_start over project_restart or project_build, nor on prerequisites (is a registered projectId required?).

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