Skip to main content
Glama
Sign In
appforshare-mcp

appforshare-mcp

Official
by appforshare
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Retire a test build

retire_build
Idempotent

Mark a build as retired when it crashes or must not be installed; install links and testers move to the newest build, channels skip it, and update checks report it as retired. Add a reason or undo.

Instructions

Mark one build as retired ("use a newer build"), for example when it crashes on start: its install link takes no installs, its page sends testers to the newest build of the same app and platform, channels skip it (a channel falls back to the build before), and the update check answers retired: true and minBuild for it. Optional reason (up to 200 characters) is shown to testers. undo: true brings it back. Ask the person first and pass confirm: true. Pro and Team, Developer role.

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": {
      "build": "<build>",
      "confirm": "<confirm>"
    },
    "name": "retire_build"
  }
}

Input Schema

NameRequiredDescriptionDefault
undoNotrue brings a retired build back
buildYesBuild id or the slug of its install link
reasonNoShown to testers, for example Crashes on login, use 2.5 (122)
confirmYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.7

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations, the description discloses exactly what changes: the install link stops taking installs, the page redirects to the newest build of the same app/platform, channels skip it and fall back to the prior build, and the update check returns retired: true with minBuild. It also states reversibility (undo: true), the visibility of the reason to testers, and the plan/role requirement, all of which are consistent with idempotentHint=true and destructiveHint=false.

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 action and effects are front-loaded in the opening clause, and each subsequent clause carries distinct operational information (link, page, channels, update check, reversibility, permissions). It is dense and long for a single paragraph but contains no filler sentences.

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 four-parameter mutation with no output schema, the description covers effects, reversibility, authorization requirements, and tester-visible side effects, which is close to complete. The only gap is what the call returns on success or failure, which an agent calling this could reasonably want.

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?

With 75% schema description coverage, the schema already documents undo, build (id or install-link slug), reason length and audience, and the confirm constant. The description largely restates those rather than adding format or edge-case detail; its only marginal addition is the instruction to ask the person before confirming.

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?

"Mark one build as retired" gives a specific verb and a precise scope (one build), and the enumerated consequences (install link, build page, channels, update check) make clear what retirement means as opposed to deletion. It does not explicitly name a sibling such as delete_build as the contrasting option, so the differentiation is implied by effects rather than stated.

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 concrete triggering situation ("for example when it crashes on start") plus prerequisites: ask the person first, pass confirm: true, Pro/Team plan, Developer role. It also notes undo: true reverses it. There is no explicit statement of when NOT to use it (e.g., permanent removal instead), which keeps it below 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