Server Quality Checklist

Tool Scores

• transcribe_audioA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral disclosure burden. It does well by revealing that processing is fully local, audio is not uploaded to any cloud service, and the first model load takes about 40 seconds with a mitigation path. It does not describe output details, but an output schema exists to cover that.

  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 three short sentences with no filler: core purpose, privacy behavior, and latency mitigation are each given exactly one sentence. It is front-loaded and easy to scan.

  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 relatively simple tool with one required parameter and an output schema, the description covers purpose, supported formats, local processing, privacy, and the relevant sibling relationship. The main gap is parameter-level guidance for with_timestamps, but the boolean name and schema default provide enough signal for correct invocation.

  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 needed to compensate for parameters like file_path, traditional, and with_timestamps. It only implicitly hints at traditional via 繁體中文 and at file_path via 本機音檔, while with_timestamps is never explained. An agent would have to rely on parameter names and defaults 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 states a clear verb and resource: converting local audio files into Traditional Chinese transcripts. It also lists supported formats and implicitly differentiates itself from the sibling preload_model by describing the actual transcription task.

  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 clearly establishes when to use the tool: whenever a local audio file needs a Traditional Chinese transcript. It also gives an explicit conditional alternative: call preload_model first if the user cares about the ~40s model loading delay. No when-not-to-use scenario is stated, but there are no competing transcription siblings.

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

• preload_modelA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that the tool loads a model into memory, that the first execution downloads ~1.5GB of weights, and that calling it when already loaded has no side effects. This meaningfully informs the agent about cost, statefulness, and safety.

  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 three short sentences with no filler. The primary purpose is front-loaded, followed by the most important behavioral caveats (download size and idempotence). Every sentence contributes useful information.

  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 zero-parameter tool with an output schema and a single sibling, the description covers what the tool does, why it should be used, the main cost, and its side-effect behavior. Nothing essential is missing for an agent to decide when to invoke it.

  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 no parameter-level detail, but none is needed; the empty input schema and the description are fully consistent and sufficient.

  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 states a specific action ('預先把 FunASR 模型載入記憶體') with a clear purpose ('讓之後的 transcribe_audio 呼叫可以立即開始辨識'). It clearly distinguishes itself from the sibling transcribe_audio by describing a preloading step rather than the recognition step itself.

  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 clearly implies when to use the tool: before transcribe_audio calls to make them start immediately. It also provides relevant usage context about the first-run download and the idempotent nature when the model is already loaded, though it does not explicitly list exclusion cases or alternatives.

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