Skip to main content
Glama

Ask Muse Code (new session) [experimental]

muse_ask

Send a trusted prompt to Meta's Muse Spark model as a sub-agent in a new session; set the workspace for repo access, choose sandbox mode, then follow up with muse_continue.

Instructions

Best for Meta's Muse Spark models (Muse Code, muse exec), in a NEW session. EXPERIMENTAL: the real model has never answered through this bridge (its offline echo provider verified the rest), so if it misbehaves say so plainly. Needs a Muse plan (muse login) or META_API_KEY; run muse_status first. Pass workspace=; without it the sub-agent sees no repo. Follow up with muse_continue. read-only switches its write/shell/web tools off on every OS. 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_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoOptional model id (`--model`, e.g. "muse-spark-1.3"). Muse accepts any id, so this is not validated. Omit for muse's default.
watchNoIf true, open a live "watch" view of muse's task stream. Same final text is returned. Best-effort. Default false.
promptYesQuestion or instruction for Muse. Passed in a file, never argv.
sandboxNo"read-only" (default — muse's write, shell and web tools switched off, so it can only read and answer; holds on every OS), "workspace-write" (shell runs inside muse's OS sandbox, network proxy-only; on Windows that sandbox needs a one-time elevated setup — see muse_status), or "danger-full-access" (`--yolo`: no approval, no sandbox — avoid).read-only
timeout_sNoMax seconds to wait for muse to complete. Default 180.
workspaceNoWorking root (`--workspace`). Defaults to the server cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.32.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false, openWorldHint=true, idempotentHint=false; the description adds much more — an EXPERIMENTAL warning that the real model has never answered through this bridge, the auth requirements, the sandbox behavior per mode and per OS, and the note that `read-only` disables write/shell/web tools. That is behavior beyond what structured fields convey, and it does not conflict with the annotations.

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 experimental caveat and auth prerequisite come first, then usage rules, then follow-up routing — well front-loaded with no wasted sentences. The aside about the offline echo provider is slightly chatty for the value it adds, keeping it short of a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating, open-world agent-invocation tool with a rich output schema, the description covers what an agent needs: prerequisites, workspace requirement, sandbox risk trade-offs, timeout default, and session continuity. Return-value detail is rightly left to the output schema.

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 schema already documents all six parameters and the baseline is 3. The description still adds real meaning the schema lacks: that the workspace root determines whether the sub-agent sees a repo at all, and that `read-only` disables write/shell/web tools on every OS rather than just being a label.

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?

The description establishes the exact scope: ask Meta's Muse Code model in a NEW session, with 'Follow up with muse_continue' defining the boundary against its closest sibling. Combined with the title and the required `prompt` parameter, an agent can tell what the tool does and which alternative handles the continuing-session case without opening either schema.

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?

It gives explicit preconditions and ordering ('Needs a Muse plan (`muse login`) or META_API_KEY; run muse_status first'), names the follow-up tool, and warns 'Autonomous agent: trusted prompts only.' It also supplies a concrete routing rule for the key parameter ('Pass workspace=<project dir>; without it the sub-agent sees no repo').

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