Skip to main content
Glama

body_speak

Speaks text aloud through the local system voice without network or downloads; playback runs in the background and can be stopped when needed.

Instructions

Speak text with the LOCAL system voice (Windows SAPI - no download, no network).

Playback runs in the background and can be stopped with body_stop_speaking(). Typed chat stays fully usable without this; the tool never sends audio anywhere.

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": {
      "text": "<text>"
    },
    "name": "body_speak"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
voiceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the whole burden and does well: it discloses that playback is asynchronous/background, that chat remains usable concurrently, and that audio is never transmitted anywhere. Undisclosed are the edge behaviors an agent would care about — what happens on a second call while speech is active (queue vs. interrupt) and what occurs if the requested voice is unavailable.

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?

Two short sentences, the hard constraint (local/no network) front-loaded, followed by the operational note about stopping and concurrency. Nothing is padded and the parenthetical is doing real work rather than restating the name.

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

Completeness3/5

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

Behavioral context is solid for a simple side-effecting tool with no output schema, but the definition is incomplete on the `voice` parameter, leaving an agent unable to pick a non-default voice without guessing or probing a sibling tool. One sentence on voice identification would close the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the two parameters and does not. It never says what `text` accepts (length limits, SSML, plain text) nor what `voice` means or what the empty-string default selects, which is the single most confusing aspect of the call.

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 definition leads with a specific verb and resource ("Speak text") and pins down the mechanism and scope: "LOCAL system voice (Windows SAPI - no download, no network)". That contrast with network/download-based speech is exactly what separates it from other voice-related siblings, so an agent can classify it immediately.

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 operating context (local, offline, no download) and names the paired escape hatch, body_stop_speaking(), so the agent knows how to interrupt playback. It gives no explicit exclusions or routing to alternatives such as a voice-listing sibling for choosing a non-default voice, so it falls short of full when/when-not guidance.

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