Skip to main content
Glama

List voices

list_voices
Read-onlyIdempotent

List the voices that can speak the audio of a language: the same ones the audio window of the editor offers, each with its name, gender and locale (es-ES Spain, es-MX Mexico, es-US United States...), and "high_quality" for the ones the editor marks so. It also gives the speeds with the names the editor shows and, in "user_preference", the voice and speed the user chose last in that language, which generate_field_audio uses when it gets no audio_config. Call it when the user asks which voices there are, or asks for a voice by its gender or accent, to pick its name. With "fallback_language", the language has no voices of its own and its audio is read by these.

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": {
      "language": "<language>"
    },
    "name": "list_voices"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageYesISO 639-1 code: the "lang" of the activity, or the language the user named.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: the exact fields returned (name, gender, locale with examples like es-ES Spain, high_quality flag), that speeds are included under the editor's display names, and that user_preference carries the last-chosen voice and speed used by generate_field_audio when no audio_config is supplied. That is real disclosure about return content and cross-tool effect, not a restatement of 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 purpose is front-loaded in the first clause and the sentences are dense but information-bearing, with no filler. It runs long as a single flowing block for a one-parameter tool, and the closing 'fallback_language' sentence is the least clear part of the structure.

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?

With no output schema, the description correctly takes on the burden of describing the return shape (name, gender, locale, high_quality, speeds, user_preference), which is what an agent needs before calling. The one gap is 'fallback_language', which is neither in the schema nor clearly identified as a response field, leaving its role ambiguous.

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% for the single 'language' parameter, so the schema already carries the semantics and a baseline 3 applies. The description's locale examples (es-ES Spain, es-MX Mexico) loosely illustrate what a language code resolves to, but the mention of 'fallback_language' does not map to any declared parameter, adding ambiguity rather than meaning.

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 opens with a specific verb and resource ('List the voices that can speak the audio of a language') and immediately scopes it against the editor's audio window, so an agent knows exactly what set is returned. It also names the downstream consumer (generate_field_audio) that relies on the user_preference field, which separates this tool from the sibling generate_field_audio.

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 concrete trigger conditions: 'when the user asks which voices there are, or asks for a voice by its gender or accent, to pick its name.' That is clear when-to-use guidance tied to a user intent. It stops short of stating exclusions or a direct 'use X instead' for the closest sibling, so it is not a full 5.

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.

Resources