Skip to main content
Glama

disconnect

Idempotent

Sign off from the current screen's command line and close the IBM i session so the host job does not stay active. If the screen has no command line, report that signoff is unavailable.

Instructions

Sign off (from the command line of the current screen) and close the session. A screen without a command line can't be signed off from; the result says so.

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": "disconnect"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionNosession name; lets you run several side by sidemain
signoffNosign off first from the screen's command line, so the job doesn't stay active on the host

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (non-destructive, idempotent, not read-only), so the description's job is to add context — and it does: it explains the command-line signoff step and discloses the failure mode (screens without a command line can't sign off, and the result reports that). It doesn't say what happens to running jobs or recordings on close, which is a remaining gap.

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 sentences, both front-loaded and free of padding; the primary action comes first and the constraint second. The phrasing "can't be signed off from; the result says so" is slightly awkward but carries real information rather than filler.

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?

With an output schema in place, return details needn't be described, and both parameters are documented. The description supplies the one non-obvious operational constraint (no command line means no signoff) and notes that this is reported back, leaving only session-teardown side effects unstated.

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 both 'session' (name, side-by-side runs) and 'signoff' (avoids leaving the job active on the host) are already fully documented. The description reinforces the signoff concept but adds no new syntax, defaults, or interaction semantics beyond the schema, so the baseline 3 applies.

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?

The description gives a specific verb and resource: "Sign off ... and close the session." Combined with the tool name 'disconnect' and the parameter set, an agent can tell this terminates a named session rather than connecting to one. It stops short of naming a sibling alternative, but the action is unambiguous.

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 rather than stated: call it when you want to end a session, and the description adds the precondition that the current screen needs a command line for signoff. There is no explicit when-not-to-use guidance or pointer to a sibling (e.g. how this differs from simply abandoning a session), so the agent must infer the boundary.

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