Skip to main content
Glama

workspace_open

Idempotent

Open or reattach to an isolated workspace on a chosen fleet or image. Call explicitly to pick a fleet, image, or guarded fleet; exec, read_file, and write_file attach to it automatically.

Instructions

Open (or reattach to) your isolated workspace on a fleet. exec, read_file and write_file use it automatically, and open one on an unguarded default fleet when none exists, so call this explicitly only to pick a fleet or image, or for a guarded fleet. On a guarded fleet you must first ask the user and get their explicit agreement; only then set confirm to the fleet name.

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": "workspace_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
fleetNoFleet name. Omit to use the default.
imageNoImage from the fleet allowlist. Omit for the fleet default.
labelsNoRunner labels the workspace must land on.
confirmNoGuarded fleets only: the fleet name, set only after the user explicitly agreed. Never set it on your own.
contextNoContext name. Omit to use the default.
credentialsNoHost-mode fleets: narrow the session to these credential names (a subset of those the runner holds). Omit to use all.

Output Schema

NameRequiredDescriptionDefault
whereYes
reusedYes
workspaceYes
session_sourceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already mark this as non-read-only, open-world, idempotent and non-destructive, and the description adds real context beyond them: workspaces are auto-provisioned when absent, calls reattach rather than duplicate, and guarded fleets require user consent. The one remaining gap is that it says nothing about workspace lifetime or what state a reattach inherits, so it stops just short of full disclosure.

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 core action, then the auto-invocation caveat, then the guarded-fleet escalation rule, in priority order. The first sentence is a long run-on that takes effort to parse, but no sentence is padding.

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 6-parameter tool with a full output schema, the description covers the parts that actually need prose: default behavior, when to call explicitly, and the guarded-fleet consent protocol. It is silent on labels, credentials and context, which are left entirely to the schema's own descriptions, which is acceptable but leaves host-mode narrowing unexplained.

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 100%, so the baseline would be 3, but the prose embeds fleet and image into the decision rule ('pick a fleet or image') and frames confirm as a consent artifact rather than an ordinary field. It adds workflow meaning to the parameters even though the field-level text is already in the schema.

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?

Starts with a specific verb and resource ('Open (or reattach to) your isolated workspace on a fleet') and immediately distinguishes itself from the implicit path used by exec/read_file/write_file. An agent can tell what this does and why it would exist separately from its siblings.

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 an explicit when-not rule ('call this explicitly only to pick a fleet or image, or for a guarded fleet') plus the guarded-fleet precondition: ask the user and get explicit agreement first, then set confirm. That is a precise routing and gating instruction rather than an implied usage.

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