Server Quality Checklist

Tool Scores

• analyze_imageA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that local files are sent inline as base64 data URLs with a 25MB guardrail, which is useful behavioral context. However, it does not mention return format, side effects, or error handling, leaving significant behavioral aspects undisclosed.

  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 sentences, each earning its place: purpose, when to use, and input details. It is front-loaded with the action and avoids redundancy. No fluff or excessive detail.

  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?

  There is no output schema, so the description should convey the expected output implicitly. It adequately covers the main input, use case, and a key constraint (25MB guardrail). However, it omits response format and potential error conditions, which would be useful for a tool with no output schema. Overall, it is sufficiently complete for its complexity.

  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 adds meaningful detail for `image_url`, explaining that it can be a public URL or local path, and that local files are base64-encoded with a size limit. It also names the underlying model, which informs parameter behavior. This goes beyond 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 description clearly states 'View, read, or analyze an image' and identifies the specific model (Qwen3.8-Max). It distinguishes from sibling tools that target video/audio, making the resource and action unambiguous. The concrete example ('[Unsupported Image]') further clarifies the purpose.

  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 explicitly says 'Use this whenever you need to see an image you cannot view natively', providing a clear condition for use. It gives a concrete scenario but does not name sibling tools as alternatives, though the image focus implicitly excludes video/audio. No explicit 'when not to use' beyond the native viewing case.

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

• check_endpoint_statusA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It discloses that the API key is redacted in the output, a key behavioral trait. It does not mention side effects or network calls, but for a simple read-only check, this is sufficient.

  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 a single sentence that conveys the purpose and a key behavior (API key redaction). No wasted words.

  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?

  Given no parameters and no output schema, the description provides the core functionality and one output detail. It is sufficient for a simple check tool, though it could mention return format.

  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, and schema coverage is 100%, so the baseline is 4. The description adds nothing about parameters, but none exist.

  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 clearly states the tool checks the configured Bailian endpoint, model, and timeout, with a verb ('check') and specific resources (endpoint, model, timeout). It distinguishes itself from video analysis and capabilities tools.

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

  Usage Guidelines3/5

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

  The description does not provide when or when not to use this tool, nor does it mention alternatives. However, the context signals show distinct sibling tools, so usage context is implied but not explicit.

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

• analyze_audioA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the transparency burden. It discloses meaningful behavioral traits: accepted URL/file paths, inline base64 sending, a 25MB guardrail, supported formats, and the specific model. It does not mention response format or potential limitations, but for a read-only analysis tool the disclosed constraints are substantial.

  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-loaded with the core action, and every sentence earns its place. It conveys purpose, usage context, and key input constraints in just two sentences without 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?

  Given the absence of an output schema and annotations, the description covers the essential context: what the tool does, when to use it, accepted input forms, formats, and size limits. It does not describe the response structure, but that may be predictable for an analysis tool. The level of detail is appropriate for the tool's complexity.

  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 adds value beyond the schema by explaining that local files are sent inline as base64, specifying the 25MB guardrail, and listing supported file extensions. This operational detail is not present in the schema's description of audio_url.

  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 names a specific verb+resource ('Listen to and analyze an audio file') and identifies the underlying model (Qwen3.5-Omni). It clearly distinguishes from sibling tools like analyze_image and analyze_audio_video by scoping to audio only and mentioning native audio understanding.

  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 explicitly says 'Use this whenever you need to hear audio you cannot process natively,' providing clear when-to-use context. However, it does not mention when not to use it or name alternatives, such as analyze_audio_video for files that also contain video.

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

• analyze_audio_videoA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does a strong job: it names the underlying model (Qwen3.5-Omni), states native audio+video understanding, and discloses how local file paths are handled (base64 data URL) plus a 25MB guardrail. It omits some details like authentication or output structure, but covers important operational behavior well.

  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 sentences, each earning its place: the first defines what the tool does, the second explains when to use it, and the third details input formats and a size constraint. No filler or repetition, and the most important information 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?

  Given 4 parameters fully covered in the schema, no output schema, and no annotations, the description is fairly complete: it covers the task, model, input flexibility, and a key constraint. It does not explain the output format or potential errors, but for a Q&A-style multimodal tool, the expectations are reasonably clear.

  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 baseline is 3, but the description adds genuinely useful semantics beyond the schema: it clarifies that video_url accepts public URLs or local paths, that local files are sent inline as base64, and explicitly notes the 25MB guardrail. This supplements the raw property definitions meaningfully.

  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 ('Watch and listen') and resource ('a video'), and explicitly includes both visuals and audio track, which immediately distinguishes this tool from analyze_video and analyze_audio. The verb+resource combination is precise and independently meaningful.

  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?

  Gives explicit usage criterion ('Use this when what is said or heard in the video matters'), which clearly implies when this tool should be chosen over visual-only or audio-only siblings. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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

• analyze_videoA
  4.4/5.0
  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. It discloses a key behavioral trait: 'The model reads the video natively — no client-side frame extraction,' which sets expectations about processing. It also discloses the 25MB base64 guardrail for local files. While it doesn't cover error handling or response format, for a read-only analysis tool these are minor gaps.

  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 efficiently written in four sentences, each serving a purpose: purpose, usage, processing behavior, and input format. It is front-loaded with the core function, and no words are wasted. This is a model of concise, informative documentation.

  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?

  Given the lack of output schema, the description is very close to fully complete. It explains what the tool does, when to use it, how it processes, and input constraints. The only small gap is not explicitly stating the return format, but that is implied by the question parameter and the analysis context. Overall, it is highly informative for a tool without annotations.

  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 adds meaningful info beyond the schema: it clarifies that video_url can be http/https or a local path, and that local files are sent as base64 data URL with a 25MB limit. This extra context helps the agent understand the parameter's constraints and behavior.

  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 the exact function: 'Watch and analyze a video using Qwen3.8-Max (native multimodal).' It clearly distinguishes this tool from siblings like analyze_image and analyze_audio, focusing specifically on video. The verb 'watch and analyze' plus resource 'video' makes the purpose unambiguous.

  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 explicitly says 'Use this whenever you need to see a video you cannot view natively,' providing clear when-to-use guidance. It also gives practical input guidelines (public URL or local file path, base64 inline, 25MB guardrail). It does not explicitly mention alternatives or when not to use, but the context is sufficiently clear.

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