Swipium

Overview Schema Source Related Servers Discussions Admin

Resolve a build artifact

qa_resolve_artifact

Read-only

Locate and rank installable Android or iOS build artifacts from Gradle, Flutter, or Xcode outputs, returning candidate paths, build types, app IDs, and warnings without modifying files.

Instructions

Find the best installable build (.apk/.aab/.ipa/.app) in Gradle/Flutter/Xcode outputs. Returns ranked candidates (build type, installability, app id, warnings) and the paths searched. Side-effect free.

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_resolve_artifact"
  }
}

Input Schema

Name	Required	Description
`path`	No	Explicit artifact path; skips the search.
`platform`	No
`buildType`	No
`sessionId`	No	Use this session's projectRoot if given.
`projectRoot`	No	Absolute path; else the usual root resolution.
`allowOutsideRoot`	No	Allow a candidate outside the project root.
`requireInstallableOn`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A3.7/5.0

Behavior4/5

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

With readOnlyHint=true already declared, the description still adds real value: 'Side-effect free' reinforces the safety profile, and it discloses the return shape ('ranked candidates (build type, installability, app id, warnings) and the paths searched') that no output schema provides. It stops short of saying what happens when nothing is found or how candidates are ranked.

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 waste, front-loaded with the core action and followed immediately by the return contract and the side-effect guarantee. Dense but fully earned.

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?

A 7-parameter discovery tool with no output schema is reasonably served by the disclosed return shape and read-only guarantee. But the ranking criteria and the no-result behavior are unstated, and the boundary parameter `allowOutsideRoot` is left semantically unexplained.

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 57%, below the 80% baseline, so the description should carry more of the load. It clarifies that `path` bypasses the search and that some root scoping exists, but `platform`, `buildType`, `requireInstallableOn`, and `allowOutsideRoot` get no added meaning beyond their enum names.

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 ('Find the best installable build') plus the concrete artifact types and ecosystem sources (Gradle/Flutter/Xcode outputs). It is clearly distinguishable from a plain artifact getter, though it never names a sibling such as qa_get_artifact to route the agent 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?

Implied usage: 'Find the best installable build' plus the note that an explicit `path` 'skips the search' tells the agent it is a discovery tool, not a fetch tool. However, there is no explicit when-to-use/when-not statement and no named alternative for the case where the agent already knows the artifact.

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