Skip to main content
Glama

Continue GitHub Copilot session

copilot_continue

Resume a prior coding session with the same workspace and a follow-up prompt, then switch sandbox permissions from read-only to workspace-write when you need fixes applied.

Instructions

Continue the Copilot session: resumes the thread rooted at this workspace (its --session-id), so pass the same workspace= as the ask (without it the sub-agent sees no repo). After a restart it resumes the newest on-disk session for that directory. sandbox applies per turn: analyze read-only, then continue with "workspace-write" to apply the fix. Autonomous agent: trusted prompts only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "copilot_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
watchNoIf true, open the live "watch" view streaming copilot's steps (same viewer as copilot_ask). Default false.
promptYesFollow-up message for the existing session.
sandboxNoPermission policy for THIS turn (default "read-only"). Same values and caveats as copilot_ask.read-only
timeout_sNoMax seconds to wait for copilot to complete. Default 180.
workspaceNoWorking root used by the prior session. Defaults to the server cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.15.4

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true) it discloses session-resume semantics, including that after a restart it resumes the newest on-disk session for that directory, and that sandbox applies per turn. The 'trusted prompts only' warning adds a security caveat the annotations do not convey. It does not describe failure behavior when no session exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the core action, but the remaining text is a dense multi-clause run-on mixing CLI flag references ('--session-id'), restart behavior, sandbox escalation, and an autonomy caveat. The backticked flag detail is noise for an agent invoking an MCP parameter.

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?

Output schema exists, so return values need not be explained. The description covers session identity, workspace coupling, per-turn sandbox, and the autonomous-agent caveat, which is enough for correct invocation. Missing is what happens if no resumable session exists for the workspace.

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 baseline is 3, but the description adds real meaning: workspace must match the prior session's root or the agent loses repo context, and sandbox is re-evaluated each turn with the workspace-write escalation pattern. Those are semantic constraints the schema descriptions do not state.

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 states a specific verb and resource ('Continue the Copilot session: resumes the thread rooted at this workspace'), which clearly separates it from starting a fresh session. It refers to the prior 'ask' rather than naming copilot_ask explicitly, so sibling differentiation is implied rather than spelled out.

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?

It gives a concrete usage condition (pass the same workspace=<project dir> as the original ask, otherwise the sub-agent sees no repo) and an escalation pattern (analyze read-only, then continue with workspace-write). It stops short of explicitly saying when to prefer this over copilot_ask for a new thread.

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