Skip to main content
Glama
Sign In
appforshare-mcp

appforshare-mcp

Official
by appforshare
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

GitHub build runs and why one failed

github_build_run
Idempotent

Lists GitHub Actions build runs for iOS and Android, or details one run with AI explanations and fix steps for failed jobs so you can diagnose errors fast.

Instructions

iOS and Android builds AppForShare started on the workspace's GitHub Actions. Without run: the recent runs, newest first, with their result. With run (an id from that list): that run, and for a failed one the AI explanation of the likely cause and the fix steps, written from the failed job's log with secrets taken out (shown when AppForShare already made one). Pass explain: true to make one when there is none (1 AI action of the account, Developer role); it never changes code or the repository. Pro and Team.

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": "github_build_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNoRun id from the list
limitNo
explainNoMake the AI explanation of a failed run when there is none (1 AI action)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.7

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations it discloses costs and side effects: one AI action charged per generated explanation, Developer role required, Pro/Team plan gating, secrets stripped from the failed job's log, and an explicit guarantee that it never changes code or the repository. This resolves why readOnlyHint=false even though the tool is non-destructive, which the annotations alone would leave ambiguous.

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?

Sentences are front-loaded by mode (no run / with run / explain) and every clause carries operative information: ordering, redaction, cost, permissions, and plan. Nothing is redundant with the title or with structured fields.

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, the description does carry the return-value burden and does so ('recent runs, newest first, with their result' and the single run plus explanation). It does not describe what 'result' contains or how 'limit' interacts with the list, leaving a small gap for a three-parameter, open-world tool.

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 67%, and the description compensates by explaining that 'run' must come from a prior list result and that 'explain' triggers a billable AI action only when no explanation exists. The 'limit' parameter is left to the schema, which already carries default, minimum, and maximum, so the remaining gap is minor.

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?

The description names the concrete resource ('iOS and Android builds AppForShare started on the workspace's GitHub Actions') and states two distinct operations: listing recent runs and retrieving/explaining a single run. An agent can tell what it does without opening the schema, and the dual-mode framing separates it from the build listing/upload siblings.

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 gives explicit mode selection rules: omit 'run' for the recent list, pass an id 'from that list' for a single run, and add 'explain: true' only when no explanation exists yet. It also adds an eligibility constraint ('Pro and Team') and a role constraint ('Developer role'). It stops short of naming alternative tools for other build queries, so it is clear context without sibling routing.

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