Generate a short TTS preview. Hosted mode returns a download URL.
Args:
voice_id: Voice id from `list_voices`.
output_path: Output filename hint (hosted) or WAV path (stdio).
language_code: Optional locale.
text: Optional preview line (max 200 chars).
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | ||
| voice_id | Yes | ||
| output_path | No | preview.wav | |
| language_code | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the important behavioral split: hosted mode returns a download URL while stdio writes to a WAV path. It omits permissions, cost/latency implications of TTS generation, and whether previews are cached or overwrite existing files at output_path.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The behavioral summary is front-loaded in two short sentences, followed by a scannable Args block with no filler. The docstring-style indentation is slightly verbose but each line adds parameter meaning rather than repeating the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so the description rightly avoids detailing return values while still flagging the download URL case. For a 4-parameter generation tool with no annotations, the main remaining gap is routing guidance versus the synthesize_audio siblings and any file-overwrite behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description compensates well: it ties voice_id to list_voices, explains that output_path is a filename hint in hosted mode but a real WAV path in stdio, and bounds text at 200 characters. Only language_code ('Optional locale') remains thin relative to what an agent might need, such as format or fallback behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Generate a short TTS preview') plus the mode-dependent return ('Hosted mode returns a download URL'). It does not explicitly distinguish itself from sibling synthesize_audio / synthesize_audio_advanced, so an agent must infer that 'preview' is the short, throwaway variant.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use or when-not-to-use guidance is given; the description never says to prefer this over synthesize_audio for short samples or the reverse. The max-200-chars note on text implies a lightweight use case, but that is inference rather than stated guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.