Skip to main content
Glama
Sign In
Swipium

Swipium

by GeroPalombo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Plan or run a build from source

qa_build

Plans or runs Android and iOS app builds from source, reports toolchain status, expected artifacts, and stores build logs; failures are typed as build errors, not test failures.

Instructions

Build the app from source. mode:"plan" (default, no side effects): commands, cwd, expected artifacts, toolchain status. mode:"run" (consent-gated job, needs sessionId): runs them, stores the build log, re-resolves the artifact. Failures are typed (GRADLE_FAILED, XCODEBUILD_FAILED, ...) and are not test failures.

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": {
      "platform": "<platform>"
    },
    "name": "qa_build"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo
approveNorun
variantNo
platformYes
consentIdNorun
sessionIdNoRequired for run (stores the build log).
timeoutMsNorun: per-step timeout (default 1200000).
projectRootNoplan: resolve the project without a session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well past the annotations (readOnly=false, destructive=false, idempotent=false) by disclosing that plan has no side effects, that run requires consent plus a sessionId, that the build log is persisted, that the artifact is re-resolved, and that failures carry typed codes distinct from test failures. This is the behavioral detail an agent needs before triggering a mutating job.

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?

Front-loads the core action, then enumerates the two modes in tight parallel clauses with no filler. The inline quoting of mode values is slightly noisy but functionally dense.

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?

With no output schema and eight parameters, the description covers both modes' outcomes, the consent requirement, log storage, and the error taxonomy. It does not describe what a successful run returns (job handle, artifact reference), which is the main remaining gap.

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?

Adds meaning beyond the 63%-covered schema: it explains what plan returns (commands, cwd, expected artifacts, toolchain status) and which parameters gate run (sessionId, consent). Variant, timeoutMs, projectRoot, and the bare approve/consentId fields get no narrative treatment, leaving some parameters dependent on terse schema text.

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?

Opens with a specific verb and resource ("Build the app from source") and immediately splits the tool into two well-defined modes with distinct outputs. An agent knows exactly what the tool does, though it never contrasts itself with nearby build-related siblings such as qa_app_map_build, qa_bundletool, or qa_metro.

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?

Clearly signals when to pick each mode: plan is the default with no side effects, run is consent-gated and needs a sessionId. That gives real use/no-use context, but no explicit routing to alternative build or inspection tools, so it stops short of a 5.

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

Deploy Server

Other Tools