Skip to main content
Glama

Connect Varity

varity_login
Idempotent

Connects this computer to Varity so deployments work, handling browser sign-in or deploy-key setup and returning a link and code for browserless devices.

Instructions

Connect Varity on this computer, so deploys work. When browser sign-in is switched on, tell the user before calling: "I'll open a browser tab: confirm there to connect Varity." and confirming in the browser is the only step. When it is not, the call answers SIGN_IN_UNAVAILABLE: then relay its message, which connects with a deploy key added to the editor's MCP settings, never typed into chat. The call waits up to 2 minutes; if it returns status "pending", relay its message to the user and call varity_login again to finish the same sign-in. On a machine without a browser it returns a link and a short code for the user to confirm on any device. Never ask the user for a key; credentials are never accepted as tool input.

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": "varity_login"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.0.0
    • removedInput schema / properties / deploy_key
      Removed value: -{
      -  "description": "Your deploy key from the Varity developer portal (developer.store.varity.so/dashboard/settings). If omitted, this tool opens the settings page in your browser, copy your key from there, then call varity_login again with the key.",
      -  "type": "string"
      -}
  2. First observedv2.0.0-beta.24

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations, which only say it is a non-read-only, non-destructive, idempotent call. The description discloses the up-to-2-minute wait, the SIGN_IN_UNAVAILABLE and "pending" outcomes, the deploy-key path through MCP settings, the headless link-and-code fallback, and that credentials are never accepted as input — exactly the operational context an agent needs before invoking an auth tool.

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 sequenced by execution path (browser on, browser off, pending, headless). Slightly heavy, and the closing "Never ask the user for a key" partially restates the earlier deploy-key sentence, but no sentence is 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 zero-parameter sign-in tool with no output schema, it covers every branch an agent can hit: success prompt, unavailable sign-in, pending retry, and browserless machines. Nothing needed to call it correctly is missing.

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?

With zero parameters the baseline is 4, and the description usefully reinforces it by stating that credentials are never accepted as tool input, so an agent will not try to invent a key argument. There is no per-parameter detail to add beyond that.

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: "Connect Varity on this computer, so deploys work." It scopes the operation to this machine and ties it to the deploy workflow, which separates it from siblings such as varity_logout or varity_deploy without needing their schemas.

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?

Gives clear when-to-use framing (before deploys, and re-call on "pending") plus branching guidance for the browser and no-browser cases. It does not explicitly say when not to use it or point at varity_logout for disconnecting, so it stops short of full alternative routing.

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