Skip to main content
Glama

workspace_close

DestructiveIdempotent

Closes a workspace and frees its runner slot, waiting on the runner or leaving the reaper to finish cleanup. Optionally deletes the session directory for host-mode fleets.

Instructions

Close your workspace and free its runner slot. state "closing" means the runner could not be reached yet and the reaper will finish the job.

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_close"
  }
}

Input Schema

NameRequiredDescriptionDefault
fleetNoFleet name. Omit to use the default.
deleteNoHost-mode fleets: also delete the session directory and everything in it. DESTRUCTIVE: set it only when the user asked for it. Without it the directory is kept and reattached on the next open.
contextNoContext name. Omit to use the default.
workspaceNoWorkspace id. Omit to use this session's workspace on the fleet.

Output Schema

NameRequiredDescriptionDefault
stateYes
whereYes
workspaceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations (which already declare destructive, idempotent, and open-world), the description adds genuinely new behavioral context: the "closing" state means the runner was unreachable and a reaper will complete the teardown asynchronously. That tells the agent the close is not always synchronous and that lingering state is expected, which no structured field conveys.

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?

Two tight sentences with the primary action front-loaded and no filler. The second sentence is a fragment beginning mid-thought ("state \"closing\" means...") which is slightly jarring out of context, but it earns its place by explaining an otherwise confusing return state.

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?

An output schema exists, so return values need no explanation, and all four parameters are fully documented in the schema. Combined with the async-close explanation, the definition is sufficient for correct invocation; only explicit routing guidance against workspace_open 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% and the delete parameter is already documented as DESTRUCTIVE in the schema, so the description adds no parameter-level meaning of its own. Baseline 3 applies when the schema carries the full load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with its effect: "Close your workspace and free its runner slot." An agent immediately knows this is the teardown counterpart to workspace_open. It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.

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

Usage Guidelines3/5

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

Usage is implied by the verb "close" and by the existence of workspace_open as the inverse, but there is no explicit when-to-use or when-not-to-use guidance, and no statement of prerequisites or what happens if the workspace is already closed (that is left to the idempotentHint annotation).

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