Server Quality Checklist

Tool Scores

• auto_enhanceA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral transparency burden. It discloses the key trait: 'Tries up to 7 strategies (upscale, sharpen, contrast, denoise, combos) in sequence — returns as soon as one succeeds.' This is concrete behavioral description, though it omits failure behavior and any safety implications.

  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 two efficient sentences, front-loaded with the core action. Every part adds value: the strategy count, sequence behavior, and ideal use case. No wasted words.

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

  Completeness3/5

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

  The tool is moderately complex, with no output schema and no annotations. The description explains the strategy sequence but does not clarify the return value format or the fact that an image source is required despite the schema listing zero required parameters. These are notable gaps for a one-call tool.

  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 fully documents each parameter. The description adds no additional parameter semantics, and it does not clarify that at least one image source (URL, path, or base64) is required despite all being marked optional 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 description clearly states a specific verb and resource: 'Automatically try enhancement strategies to decode a QR code in one call.' It distinguishes from siblings by noting it tries up to 7 strategies and requires 'no manual bbox estimation or operation selection needed,' which positions it as an automatic alternative.

  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 clear when-to-use context: 'Ideal for RETRYABLE results from decode_qrcode_full' and 'no manual bbox estimation or operation selection needed.' It implies when not to use (when manual control is desired) but does not explicitly name an alternative like enhance_and_decode.

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

• decode_qrcode_fullA
  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 and discloses key behavioral details: it scans the entire image, returns all detected codes with diagnostics, and defines a result_code decision tree. It could further elaborate on what 'detailed diagnostics' includes, but the provided behavior is sufficient for an agent.

  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—three sentences that front-load the purpose, then present a terse decision tree. Every sentence contributes value, with no redundant or filler content.

  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 an output schema and annotations, the description provides a solid decision framework with result_code mappings. It could specify the exact output structure, but the guidance is enough for an agent to act on the tool's results.

  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 coverage is 100% with rich descriptions for each parameter, including usage precedence (e.g., image_path preferred over image_url) and examples for symbologies. The description itself adds no parameter information, but the schema already handles it, so a baseline 3 is appropriate.

  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 scans the entire image for QR codes and decodes them, which is a specific verb+resource action. It adds that it returns all detected codes with diagnostics, distinguishing it from simpler or partial decode tools.

  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 guides the agent on next steps based on result_code, including a direct alternative: 'RETRYABLE → call enhance_and_decode'. It also instructs to inform the user for NO_QR_FOUND or QR_UNRECOVERABLE, providing clear usage context and alternatives.

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

• enhance_and_decodeA
  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. It discloses composable operations, the fallback when operations are omitted (crops and decodes directly), and that the enhancement strategy is agent-decided based on diagnostics. It does not explicitly state side effects (e.g., whether the original image is modified), but no annotation contradiction exists and the disclosed behavior is meaningful.

  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, using three short sentences to convey the core action, strategic context, and supported operations. Every sentence contributes meaningful information without redundancy or filler.

  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?

  The tool has five parameters and no output schema, but the description covers the main behavioral aspects: enhancement strategy, supported operations, and the optional operations behavior. It does not explain the return value, but given the tool name and siblings, this is acceptable. It is complete enough for an agent to select and invoke 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?

  Schema description coverage is 100%, so the schema already documents parameters. The description adds value by explaining that operations are composable in any order and that omitting the operations list triggers direct decode of the cropped region—information not in the schema for the operations parameter. This exceeds the baseline for high coverage.

  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's function: 'Apply enhancement operations to a region of the image, then decode.' It uses a specific verb ('apply', 'decode') and resource ('image region'), and the phrase 'Enhancement strategy is decided by the Agent based on decode_qrcode_full diagnostics' distinguishes it from decode-only and enhance-only siblings.

  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 provides clear context for when to use the tool: after obtaining diagnostics from decode_qrcode_full and when enhancement is needed. It does not explicitly mention exclusions or alternatives like auto_enhance, so it falls short of a 5 but gives solid guidance.

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