Skip to main content
Glama

Build an audio workflow

create_audio_workflow_from_intent

Build a workflow around audio the user already has. The server draws it.

Give the uploaded clips with their languages and at least one check; the clips feed the checks, then an Export. A check drops its failed clips unless you wire its fail to an Export on the canvas. Call again with confirm=true.

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": {
      "name": "<name>",
      "audio_inputs": "<audio_inputs>",
      "checks": "<checks>"
    },
    "name": "create_audio_workflow_from_intent"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesWhat the user will see it called. Ask them rather than inventing one.
checksYesAt least one: "standard" for the pair, or list them. Ask the user which.
confirmNofalse creates nothing and returns what would be created. true creates it.
audio_formatNoThe delivered audio format. Omit for the product default.
audio_inputsYesOne entry per uploaded clip, each with the language it is in and — only for a Word Accuracy or Pronunciation check — its script.
default_languageNoA fallback locale for lines that omit one, e.g. 'en-us'. Every line still needs one.

Output Schema

NameRequiredDescriptionDefault
nameNo
nodesNo
validNo
errorsNo
blockedNo
createdNo
next_stepNo
console_urlNo
workflow_idNo
not_includedNo
feature_offersNo
workspace_slugNo
workflow_summaryNo
requires_confirmationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / checks / anyOf
      Previous value: -[
      -  {
      -    "enum": [
      -      "standard",
      -      "none"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "items": {
      -      "$ref": "#/$defs/QualityCheckSpec"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "const": "standard",
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "$ref": "#/$defs/QualityCheckSpec"
      +    },
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / checks / default
      Removed value: -null
    • changedInput schema / properties / checks / description
      Previous value: -"Omit to be offered them, \"none\" for none, \"standard\" for the pair, or list them."New value: +"At least one: \"standard\" for the pair, or list them. Ask the user which."
    • changedInput schema / required
      Previous value: -[
      -  "name",
      -  "audio_inputs"
      -]New value: +[
      +  "name",
      +  "audio_inputs",
      +  "checks"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / $defs / Precede / description
      Previous value: -"Put a node immediately in front of this check, on the path it grades."New value: +"Settings for the Phoneme Injector this check is always built with."
    • changedInput schema / $defs / Precede / properties / with / description
      Previous value: -"The node placed immediately before this check. Its wiring is the server's."New value: +"The node those settings are for. It is added either way."
  3. Changed1 schema field changed
    • addedOutput schema / $defs / FeatureChoiceRow / properties / applies_to_locales
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
  4. Added

TDQS

A4/5.0
Behavior5/5

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

Beyond the annotations, it discloses that the server automatically draws the workflow, that clips feed the checks then an Export, that a check drops failed clips unless failure is wired to an Export, and that a second call with confirm=true creates the workflow. These are meaningful behavioral details for a non-readonly creation tool.

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?

The description is compact and front-loaded, with the core purpose in the first sentence and actionable behavior in the following sentences. Every sentence contributes without unnecessary repetition.

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?

The rich input schema and output schema cover most detail, and the description explains the key workflow behavior and confirmation step. It could more explicitly mention prerequisite upload steps or when to prefer this over other workflow-creation tools, but it is largely complete for the tool's complexity.

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 the schema already carries detailed parameter meaning. The description adds the relationship between audio_inputs and checks, but it does not add much parameter-specific syntax beyond what the schema provides.

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: 'Build a workflow around audio the user already has,' and adds that 'the server draws it.' That distinguishes it from manual workflow builders, though it does not explicitly name sibling alternatives such as create_workflow or create_workflow_from_intent.

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?

It gives practical invocation guidance: supply uploaded clips with languages and at least one check, then 'Call again with confirm=true.' However, it does not explicitly say when to choose this tool over create_workflow, create_workflow_from_intent, or create_workflow_from_template.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.