Server Quality Checklist

Tool Scores

• tool_get_voice_infoA
  4.2/5.0
  Behavior4/5

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

  No annotations exist, so the description carries the burden; it clearly indicates a read-only operation through 'Get', 'verify', and 'inspect'. It details the returned metadata fields and provides practical context, though it does not describe failure behavior when the voice does not exist.

  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, front-loads the operation and return fields, then adds a single actionable usage sentence. Every sentence contributes value with no redundancy.

  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?

  For a single-parameter read tool with no output schema, the description is nearly complete: it states the result fields and the recommended invocation scenario. It could mention behavior when the profile does not exist, but an agent can reasonably infer standard error semantics from 'verify a profile exists'.

  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?

  The schema already documents voice_name as 'from list_voices output', and the description adds that the same voice_name will be used with synthesize_speech. Since schema coverage is 100%, a baseline of 3 is appropriate; the description adds usage context but no new parameter format or type details.

  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 uses a specific verb and resource: 'Get full metadata of a single saved voice profile' and enumerates the exact fields returned. It clearly distinguishes itself from siblings like list_voices by emphasizing 'single' versus collection-level listing.

  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 an explicit when-to-use scenario: 'verify a profile exists and inspect its reference audio path before calling synthesize_speech.' It does not explicitly name alternatives like list_voices for listing all profiles, but the guidance is concrete enough for an agent to select this tool correctly.

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

• tool_synthesize_speechA
  4.4/5.0
  Behavior4/5

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

  With no annotations available, the description carries the behavioral transparency burden, and it does so well: it discloses the ASMR pipeline order, default passthrough behavior, when output becomes stereo, and the exact return dict fields. It slightly overstates by saying 'All ASMR params default to OFF' when highpass_cutoff_hz defaults to 60 Hz (always on), which is a minor accuracy gap.

  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 well-structured with clear sections: purpose, three usage modes, return value, and pipeline. It is dense but every sentence contributes useful information, and the most important decision (which mode to use) is front-loaded.

  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?

  For a 16-parameter tool with no output schema, the description is unusually complete: it explains usage modes, return contents, effect pipeline, and stereo behavior. The main gap is that it never explicitly states that voice_name, instruct, or both are effectively required, despite the schema only listing text as required. This could lead an agent to attempt a call with only text.

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

  Parameters4/5

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

  Schema description coverage is 100%, so the baseline is 3. The description adds genuine semantic value beyond the schema by explaining how voice_name and instruct interact in the hybrid mode, how the ASMR pipeline orders effects, and when stereo output is triggered. This goes beyond the individual parameter descriptions.

  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, action-oriented statement: 'Generate speech audio with a cloned voice OR voice design, or both.' It clearly identifies the resource (speech audio) and the two primary input sources, and the three usage modes make it easy to distinguish this synthesis tool from sibling tools like clone_voice_from_audio or design_voice.

  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?

  The three usage modes provide explicit, actionable instructions: pass voice_name only, pass instruct only, or pass both. It also references voice_name coming from a prior clone_voice_from_audio call, which helps route the workflow. However, it does not explicitly name sibling alternatives or say when not to use this tool, so it stops short of full when-vs-alternatives guidance.

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

• tool_delete_voiceA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and directly discloses the key behavioral traits: irreversibility, removal of the reference audio file, and resulting failures in list_voices and synthesize_speech. This is strong transparency for a destructive 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?

  Three short sentences with no filler. The action and irreversibility come first, followed by use cases and then downstream effects. Every sentence earns its place.

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

  Completeness5/5

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

  For a one-parameter destructive tool with no output schema, the description fully covers what is deleted, when to use it, and what changes afterward. An agent has enough information to select and invoke the tool correctly.

  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 documents the voice_name parameter as IRREVERSIBLE and states that it removes profile plus reference audio. The description adds downstream consequence context but does not need to explain parameter format.

  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 uses a specific verb and resource: 'Delete a voice profile and its reference audio file.' It clearly distinguishes this from sibling tools by stating the destructive action and permanent consequences.

  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?

  The description gives explicit use cases: 'free disk space or clean up test voices.' It does not name alternatives because no sibling deletion tool exists, and it clearly warns about the effects after deletion.

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

• tool_list_voicesA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral transparency burden. It clearly presents this as a read-only listing operation and discloses the return shape: 'list of dicts, each with name, description, language, source, created_at.' It does not discuss auth or rate limits, but those are not pressing for a no-parameter list 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: the core action appears in the first sentence, the return format is summarized in one line, and the usage guidance is a single actionable sentence. No words are wasted.

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

  Completeness5/5

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

  For a no-parameter listing tool, the description is complete. It states what the tool lists, what it returns, and provides a concrete workflow context with synthesize_speech. There are no gaps that would prevent an agent from calling it correctly.

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

  Parameters4/5

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

  The tool has zero parameters, so the baseline is 4. The description adds useful context by explaining that the returned voice_name values are what should be passed to synthesize_speech, which is more helpful than the empty input schema alone.

  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 all saved voice profiles.' It also specifies the return fields and states the tool's role in discovering available voice_name values, making it clearly distinct from sibling tools like tool_get_voice_info or tool_synthesize_speech.

  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 explicit usage context: 'Use this to discover available voice_name values before calling synthesize_speech.' This clearly tells the agent when to use this tool relative to synthesis, though it does not explicitly state when not to use it or mention alternatives like tool_get_voice_info.

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

• tool_clone_voice_from_audioA
  4.6/5.0
  Behavior5/5

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

  With no annotations provided, the description fully carries the behavioral burden and delivers rich disclosure: the exact transformation pipeline (yt-dlp download -> ffmpeg slice [ts, tf] -> 24kHz mono 16-bit PCM WAV), validation behavior (providing both modes fails; omitting both fails), overwrite semantics, voice_name slugification, and precise failure reporting ('yt-dlp/ffmpeg failure will be reported in the raised RuntimeError'). It even discloses the full return-dict shape, which is essential given there is no output schema.

  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?

  Long but exceellently structured: purpose line up front, mode blocks, numbered workflow, and error bullet list — highly scannable. Minor redundancy exists (the 5-30s ideal and 24kHz format appear multiple times across description and schema), but the length is proportionate to a 9-parameter, two-mode tool and every block serves a purpose.

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

  Completeness5/5

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

  For a high-complexity tool with no annotations and no output schema, this description is remarkably complete: it covers input modes, prerequisites, transformation side-effects, exact return keys, and all realistic failure modes. The only omissions (rate limits, timeouts) are minor for a local-file/URL pipeline, and the description compensates fully for the missing structured metadata.

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

  Parameters4/5

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

  Schema coverage is 100%, so the baseline is 3; the description still adds meaning beyond the per-property schema text by grouping parameters into modes (A: ref_audio_path; B: audio_url + ts + tf), sequencing them in a workflow ('Write the exact transcript in ref_text' before picking a name), and linking voice_name to downstream synthesize_speech calls. This cross-parameter framing helps an agent reason about parameter relationships without redundantly restating schema content.

  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?

  Opens with a specific action verb and resource: 'Save a voice profile from a reference audio (5-30s WAV ideal)'. The two input modes (local file vs URL clip) and the numbered workflow make the tool's function unambiguous, and the explicit tie to 'used later as voice_name= in synthesize_speech' positions it distinctly from siblings like list_voices, delete_voice, and design_voice.

  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?

  Provides explicit when-to-use guidance: prerequisites (5-30s clean single-speaker speech, exact transcript), a numbered 4-step workflow, mode-selection rules ('EITHER ref_audio_path OR audio_url must be provided, not both'), and common-error remedies (overwrite=True for existing voice names). It does not explicitly name tool_design_voice as the alternative when no reference audio exists, so the exclusions dimension is slightly incomplete.

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

• tool_design_voiceA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden, and it clearly discloses the key non-obvious trait: this tool does not persist a voice profile and does not use a cloned voice. It does not explicitly describe the return value or file-writing behavior, though those are partially implied by the output_path parameter.

  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?

  Three short sentences, no filler, with the core purpose and key distinction first, then usage guidance and alternative workflow. Every sentence earns its place.

  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?

  For a 15-parameter tool with no annotations and no output schema, the description covers selection, invocation, and routing to the right sibling, while the schema covers parameter details. It stops short of stating what the tool returns or writes, which would make it fully complete, but the output_path parameter fills most of that gap.

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

  Parameters4/5

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

  Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by tying the parameter set to synthesize_speech ('Same ASMR params') and by clarifying that instruct is a keyword-based design, not a cloned voice reference. That cross-tool context is genuinely useful and not already in the schema.

  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 first sentence states a specific action ('Generate speech') and a specific resource/method ('voice design keywords only (no cloned voice)'), which immediately distinguishes it from cloned-voice synthesis. It also names the sibling tools that share the ASMR parameter space, so the agent can tell this tool apart from synthesize_speech and clone_voice_from_audio.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly says to use this tool for a one-off voice without persisting a profile, and it gives the alternative workflow: clone first with clone_voice_from_audio, then call synthesize_speech with voice_name for reusable voices. This is direct when-to-use and when-not-to-use guidance.

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