Server Quality Checklist

Tool Scores

• describe_imageA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that the tool accepts various image sources and returns a text description, implying read-only behavior. However, it does not mention potential side effects, error handling, or network requirements for URLs, which are meaningful gaps for full transparency.

  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, concise sentence that front-loads the action and result, then lists the input sources. Every word is necessary, and there is 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 simple single-image description tool, the description is adequate. It covers the core purpose and input sources, and the presence of a rich output schema and 100% parameter documentation fills in the remaining details. It omits mention of prompt customization, but that is captured in the schema.

  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% for all three parameters, so the baseline is 3. The description adds no new parameter semantics beyond what the schema already documents; the mention of input sources duplicates the image parameter's description.

  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 the specific verb '识别' (recognize) with the resource '一张图片' (an image), clearly stating it returns a text description. It also enumerates the three accepted input sources (local path, URL, data URL), which effectively distinguishes it from sibling tools like describe_images_in_folder and describe_pasted_images.

  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 conveys that this tool is for recognizing a single image from local path, URL, or data URL, which implies when to use it. It does not explicitly name sibling tools as alternatives, but the context is sufficiently clear. The auto-detection of URL vs. local path in the schema further supports this.

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

• describe_images_in_folderA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses parallel execution and speed ('并行识别，速度较快'), which are useful behavioral traits. However, it does not explicitly mention read-only safety, file format requirements, or failure modes, leaving some 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 three concise sentences, each earning its place: purpose, use case, and performance trait. It is front-loaded and free of fluff.

  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 batch read tool with fully documented parameters and an output schema, the description sufficiently covers purpose, usage, and performance. Minor gaps like error handling are acceptable given the structured fields and simple read-only nature.

  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 all parameters. The description adds context about batch scanning but does not enhance understanding of individual parameters beyond what the schema provides (e.g., limit default is already in the schema). 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's function: scans all images in a folder, recognizes them in parallel, and returns a description for each. It also distinguishes from sibling tools (describe_image, describe_pasted_images) by focusing on folder-based batch analysis.

  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 explicitly states the tool is suitable for recognizing multiple images at once (e.g., putting screenshots in a folder for batch analysis), giving clear when-to-use context. It does not explicitly name alternatives, but the contrast with single-image tools is implied.

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

• describe_pasted_imagesA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description takes on the full burden. It reveals key behaviors: parallel recognition, use of actual uploaded images rather than clipboard content, and restriction to a single recent message. This gives the agent a clear behavioral model without requiring annotations.

  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 well-organized: three sentences that front-load the core function, then explain the applicable scenario and the critical constraint. Every sentence adds value 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 output schema exists and annotations are absent, the description adequately covers the main purpose, usage context, and important behavioral constraints. It could mention what happens if no images are found, but that is not essential for tool selection and invocation.

  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% with detailed property descriptions. The tool description indirectly clarifies that prompt is for recognition and max_count limits the number of images, but this is already in the schema. No additional parametric insight is provided.

  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?

  Description clearly states the action (extract pasted/uploaded images and recognize them) and the specific resource (images from the user's most recent message). It also distinguishes itself by mentioning the [Unsupported Image] scenario, setting it apart from sibling tools like describe_image or describe_images_in_folder.

  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 applicability (when images appear as [Unsupported Image] in conversation) and scoping (only the most recent user message with images). It does not explicitly name alternative tools, but the context and sibling list imply when this tool is the right choice.

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

• update_configA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full transparency burden. It discloses that the operation persists to a specific file path and that the API key will not be written to the file, a security-relevant behavioral detail. However, it does not mention merge behavior or error handling, though parameter descriptions partially cover this.

  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?

  Two sentences, front-loaded with the main action and persistence target, followed by a key security note. No redundant information 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 is relatively simple with three optional and fully self-describing parameters. The description covers persistence and API key handling, which are the key non-obvious behaviors. An output schema is present, so return-value details are not needed. Minor gap: no mention of implications if the config file is missing or unreadable.

  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%, and each parameter already has a comprehensive description (e.g., '留空则不改' meaning 'leave empty to not change'). The description adds no additional parameter-level meaning; it only contributes context about how the API key is handled, which is not a parameter.

  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 modifies and persists image recognition configuration to a specific file. The verb 'modify' plus resource 'config' distinguishes it from sibling tools like describe_image and get_config, which read or process images.

  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 establishes the tool's purpose as modifying config and persisting to ~/.deepseek-eyes/config.json, implying usage for changing configuration at runtime. It also provides a clear usage guideline about providing the API key via environment variable rather than storing it in the file. It does not explicitly exclude reading tools, but the context makes the usage obvious.

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

• get_configA
  4.3/5.0
  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 that the tool does not return the plaintext API Key, which is a significant behavioral trait, and also clarifies that it reports whether the key is set. This adds valuable context beyond the simple 'view config' purpose.

  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, well-structured sentence. It front-loads the main action, lists the key return fields, and includes the important security note about the Key, with no unnecessary words.

  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 read-only config tool with an output schema present, the description is complete. It covers the main return fields, includes the behavioral caveat about the Key, and requires no additional context to be used 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 does not need to explain parameter semantics; it appropriately focuses on the return fields instead.

  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 action (view current image recognition config) and enumerates the specific fields it returns (provider, model, Base URL, whether API Key is set). It also distinguishes from siblings by focusing on config reading, not image analysis or config updates.

  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 explicitly state when to use this tool versus alternatives. However, its role as a read-only config getter is implied by the sibling names (update_config for writes, describe_image tools for images), so usage context is inferable but not clearly articulated.

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