Retrieve Voice Sample Audio. Retrieve the first 30 seconds of voice sample audio with or without noise removal.
Bulk support: accepts voice_ids, sample_ids for batched execution.
| Name | Required | Description | Default |
|---|---|---|---|
| account | No | ||
| voice_id | Yes | ||
| sample_id | Yes | ||
| voice_ids | No | ||
| sample_ids | No | ||
| remove_background_noise | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior, and the description adds useful behavior beyond those: 30-second truncation, optional noise removal, and batched execution. No contradiction exists, though it omits details about output format, authentication, or rate limits.
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 description is compact: two sentences plus a short bulk-support note. It is front-loaded with the core action and every sentence provides useful information without redundancy.
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?
For a read-only audio retrieval tool, the description covers the key behaviors and the annotations cover safety. However, with no output schema and 0% parameter description coverage, the lack of identifier semantics, batch response format, and retrieval prerequisites leaves meaningful gaps for a six-parameter tool.
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%, so the description should compensate for the six parameters. It only mentions voice_ids, sample_ids, and remove_background_noise; the required voice_id and sample_id fields and the account parameter are left unexplained, and the relationship between single and bulk parameters is underspecified.
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?
The description uses a specific verb and resource ('Retrieve Voice Sample Audio') and adds meaningful scope ('first 30 seconds', noise removal). It does not explicitly differentiate from close sibling tools such as elevenlabs_get_audio_from_sample or elevenlabs_get_speaker_audio, so it falls just short of a 5.
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?
The description provides clear operational context: audio is truncated to 30 seconds, noise removal is optional, and bulk execution is available via voice_ids/sample_ids. However, it does not explain when to prefer this tool over related audio-retrieval siblings or state any exclusions or prerequisites.
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.
There are many tools with overlapping purposes, such as multiple voice retrieval tools (get_voice_by_id, get_voices, get_user_voices_v2, get_library_voices) and several dubbing transcript segment editors with only subtle naming differences. The inclusion of platform-level tools (authenticate, connect, marketplace) alongside ElevenLabs API tools further blurs boundaries.
Naming is highly inconsistent. Most tools have the 'elevenlabs_' prefix, but some do not (authenticate, connect, marketplace, report_bug, show_version, toolkit_info). Several tools have truncated/random suffix names (e.g., elevenlabs_dubbing_target_transcript_segmen_b565e6, elevenlabs_get_pronunciation_dictionary_ver_45baf2), and one tool is in Portuguese (elevenlabs_list_accounts). This mixture of conventions and languages makes the pattern unpredictable.
With 155 tools, the server is extremely bloated. It mixes a comprehensive ElevenLabs API surface with unrelated MCP platform tools (marketplace, authenticate, report_bug, etc.) that belong in a separate toolkit. This is a severe mismatch between the apparent purpose (ElevenLabs audio services) and the sheer number of tools.
The ElevenLabs-specific tools cover a wide range of operations (text-to-speech, voice management, dubbing, pronunciation dictionaries, Studio projects, workspace administration, order management), making it fairly complete for those domains. However, the inclusion of unrelated platform tools and the lack of a clear focus mean that an agent would have difficulty navigating this large surface, and some operations like music finetuning or speech engines appear only partially covered.