Skip to main content
Glama
Sign In

ALM X++ MCP Server

by io.github.alimbenhelal-pro
OverviewDiscussionsAdmin

ado_create_bug_from_test

WHEN: a test case failed and the failure must become a Bug in Azure DevOps. Triggers: 'open a bug for this failed test', 'crée le bug depuis le test', 'file the defect'. Builds the Bug from the test case: its steps become the reproduction steps, observed is what actually happened, and it is linked (Related) to the test case and to the requirement under test. observed must be what was really seen: no personal data. SAFE BY DEFAULT: confirm=false only shows the Bug. Call again with confirm=true after the user agreed. An open Bug with the same title is not duplicated. Needs a PAT with Work Items (Read & write).

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": {
      "testCaseId": "<testCaseId>",
      "observed": "<observed>"
    },
    "name": "ado_create_bug_from_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoOptional: Bug title. Default: '[Test failed] ' and the test case title.
confirmNofalse (default): preview only. true: create. Only after the user agreed.
projectNoAzure DevOps project. Falls back to DEVOPS_PROJECT.
expectedNoOptional: what was expected, if the test case does not say it clearly.
observedYesWhat was observed when it failed: the message, the wrong value, the screen.
severityNoOptional: 1-Critical, 2-High (default), 3-Medium, 4-Low.
testCaseIdYesId of the Test Case work item that failed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the two-phase preview/create safety model, the dedup rule (an open Bug with the same title is not duplicated), the Related links that will be created to the test case and requirement, the PAT scope needed, and a data-hygiene constraint on the observed field. None of this is inferable from readOnlyHint=false / destructiveHint=false alone.

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-loaded with WHEN and triggers before mechanics, and every clause carries information (links, dedup, PAT, PII rule). It is dense but slightly overpacked for a single paragraph, mixing trigger phrases, workflow, and constraints without visual separation.

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

Completeness5/5

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

For a mutation tool with no output schema, the description covers everything an agent needs to act correctly: when to invoke, the confirm gate, dedup behavior, side effects (links), permission prerequisites, and data constraints. The only omission is what the preview output looks like, which is minor.

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 already 100%, so the baseline is 3; the description earns extra credit by adding real semantics the schema lacks — `observed` must be the genuinely observed behavior and must contain no personal data, and `expected` is only to be supplied when the test case does not state the expectation clearly. `confirm` and `title` are only restated, not enriched.

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?

States a specific verb, resource and source: it creates a Bug in Azure DevOps from a failed test case, and it spells out that the test's steps become the reproduction steps. This is clearly distinguishable from siblings like ado_create_task or ado_record_test_result.

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

Usage Guidelines5/5

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

Opens with an explicit WHEN clause plus concrete trigger phrases in two languages, and names the alternative path (preview vs. create via confirm=false then confirm=true). The sequencing rule 'call again with confirm=true after the user agreed' removes any ambiguity about the intended flow.

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

All ALM X++ MCP Server toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources