Skip to main content
Glama

batch

Destructive

Run multiple Tonable tool actions in one call as a single undo step, with per-action results and optional stop-on-error behavior.

Instructions

Run several Tonable tools in one go, as ONE undo step (one Cmd+Z undoes them all). Each action gets its own result; a failed one does not stop the rest unless stop_on_error is set. Arguments are passed as given, so use the forms the tools document.

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": {
      "actions": "<actions>"
    },
    "name": "batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionsYesActions in order. Example: [{"command": "create_track", "params": {"name": "Bass"}}, {"command": "write_clip", "params": {"track": "t4", "slot": 0, "notes": [...]}}]
stop_on_errorNoStop at the first failed action. Default: run them all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag a destructive, non-idempotent, non-read-only operation, and the description adds real context on top: a single undo step, per-action results, and that a failure does not abort the remainder unless stop_on_error is set. It does not clarify whether a partially failed batch leaves the successful actions applied (implied yes, but unstated) or how errors appear in each action's result.

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

Conciseness5/5

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

Three short sentences, each carrying a distinct fact: scope, undo atomicity, failure isolation, and argument pass-through. The undo guarantee is front-loaded and there is no 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?

For a two-parameter wrapper with full schema documentation and no output schema, this covers the essentials an agent needs to call it. Remaining gaps are the set of permitted command names and how per-action results/errors are shaped, which matters for a tool whose payload is arbitrary other tools.

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 coverage is 100% and already documents actions, command, params, and stop_on_error with an example, so the baseline applies. The description adds one useful note — arguments are forwarded as-is, so the target tool's documented forms must be used — but says nothing about validating command names or ordering constraints beyond the schema's 'Actions in order'.

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?

States a specific verb and resource — running several named Tonable tools in a single call — plus the distinctive outcome (they collapse into one undo step). That immediately separates it from the single-purpose siblings such as write_clip or create_track.

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?

Gives a clear reason to choose batch (one Cmd+Z reverts everything) and explains the failure policy via stop_on_error, including the default of continuing. It stops short of explicit exclusions, e.g. whether batch may contain undo itself, whether it nests, or which tool names are valid commands.

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