Skip to main content
Glama

Continue Muse Code session [experimental]

muse_continue

Resume an existing Muse session by workspace after a restart and send a follow-up prompt; returns an error when no prior session exists.

Instructions

Continue the Muse session (EXPERIMENTAL): resumes the thread rooted at this workspace (after a restart, muse's own record of the newest one there), so pass the same workspace= as the ask (without it the sub-agent sees no repo). Errors rather than starting fresh when there is none. sandbox applies per turn. 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": "muse_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
watchNoIf true, open the live "watch" view (same viewer as muse_ask).
promptYesFollow-up message for the existing session.
sandboxNoPolicy for THIS turn (default "read-only"); same values as muse_ask.read-only
timeout_sNoMax seconds to wait for muse 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. Addedv0.32.1

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the safety profile is externally visible. The description adds real value beyond those annotations: the error-on-missing-session behavior, the per-turn sandbox scoping, and the 'trusted prompts only' security constraint for autonomous use. That is useful added context, but it doesn't fully compensate for the gap left by not naming the alternative tool for when the session is absent, so this settles at 3.

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?

The description is short and front-loads the verb and the resumption scope. It loses a bit to nested parentheses and the compressed 'muse's own record of the newest one there' clause, which is harder to parse than necessary, but no sentence is 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?

This is a resumption tool with an output schema and full annotation coverage, so the description doesn't need to explain returns or safety. It supplies the missing behavioral essentials: the session must exist, the workspace must match, sandbox is per-turn, and only trusted prompts should be used. Only the explicit fallback for a missing session is left implicit.

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 is 3 even without parameter prose. The description still adds meaning beyond the schema by explaining why workspace matters (without it the sub-agent sees no repo) and that sandbox applies only to this turn, rather than listing the params again.

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 opens with a specific verb and resource ('Continue the Muse session... resumes the thread') and clarifies that it resumes rather than starts, rooted at a workspace. It distinguishes the operation from a fresh start by noting it 'Errors rather than starting fresh when there is none.' The parenthetical '(after a restart, muse's own record of the newest one there)' muddies the phrasing slightly, but an agent can still tell this apart from a fresh-start sibling.

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 states the precondition clearly: a prior session must exist, and the tool errors if there is none, which implicitly routes the agent elsewhere (e.g., muse_ask) for new work. It also gives the operational instruction to pass the same workspace as the original ask, and warns that omitting it means the sub-agent sees no repo. It doesn't explicitly name the alternative tool for the no-session case, which keeps it from a 5.

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