Skip to main content
Glama

Sign in to HPE GreenLake

com_login

Sign in to HPE GreenLake so read-only com_ tools can access server data. Collects credentials through chat pop-ups and saves a GreenLake API client locally when authentication is missing or fails.

Instructions

Sign the user in to HPE GreenLake so the com_ tools work. Shows pop-ups in the chat: the user's email, then for @hpe.com accounts the number to tap in Okta Verify, or for other accounts (e.g. gmail.com) a secure local page with a masked password field. It then creates a GreenLake API client for the read-only com_ tools and saves it on this computer. Call it when a com_ tool says no COM account is configured or login failed, or when the user asks to sign in. Never ask for the password in chat; the pop-ups collect everything.

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": "com_login"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailNoPre-fills the email pop-up; the user confirms or changes it.
regionNoCOM region; detected if omitted.
workspaceNoGreenLake workspace name; asked in a pop-up if omitted and the user has several.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only say readOnly=false, destructive=false, openWorld=true, idempotent=false; the description goes much further by describing the interactive pop-up sequence, the Okta Verify branch for @hpe.com accounts vs. a masked password page for others, and that it creates and locally saves a GreenLake API client. These side effects (chat pop-ups, local credential persistence) are exactly what an agent needs and are not inferable from annotations. Minor gap: no mention of failure/retry behavior or how long the saved client persists.

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 the purpose, then the flow, then the call conditions and the password safety rule — every sentence carries information. It is slightly long for a login tool and the pop-up branch detail could be tightened, but there is no filler.

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 tool with real side effects (interactive pop-ups, credential storage) and an output schema already covering return values, the description covers what happens, why to call it, and the critical safety constraint about not requesting passwords in chat. Nothing an agent needs to invoke it correctly is missing.

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 description coverage is 100%, so email, region, and workspace (pre-fill, auto-detect, pop-up prompt when several) are already documented in the schema. The description adds only the general point that pop-ups collect everything, which reinforces but does not extend parameter meaning. Baseline 3 is appropriate.

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 and resource ('Sign the user in to HPE GreenLake') and ties it to its purpose relative to siblings: it makes the com_ tools work, whereas all listed siblings are read-only data getters. An agent can immediately tell this is the prerequisite authentication step, not a data query.

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?

Gives explicit triggers: 'when a com_ tool says no COM account is configured or login failed, or when the user asks to sign in.' It also gives an explicit prohibition ('Never ask for the password in chat') and explains that the pop-ups collect everything, leaving nothing to inference.

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