Server Quality Checklist

Tool Scores

• deepghs_list_datasetsA
  4.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering the safety profile. The description adds useful context about pagination behavior and response formats, but doesn't disclose rate limits, authentication requirements, or other operational constraints beyond what annotations provide.

  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?

  The description is well-structured with a clear purpose statement, context about available datasets, and organized parameter documentation. It's appropriately sized for a tool with multiple parameters, though the dataset examples list could be slightly more concise. Every sentence adds value to understanding the tool.

  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?

  Given the tool's complexity (5 parameters with 0% schema coverage) and the presence of output schema, the description provides complete context. It explains what the tool does, what parameters control, and what to expect in the return value. The output schema handles return value details, so the description appropriately focuses on usage context.

  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?

  With 0% schema description coverage, the description carries the full burden of parameter documentation. It provides clear explanations for all 5 parameters (search, sort, limit, offset, response_format) with examples and constraints, effectively compensating for the schema's lack of descriptions. The only minor gap is not explicitly stating that 'params' is a wrapper object.

  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 verb ('List') and resource ('all public datasets from the DeepGHS organization on HuggingFace'), providing specific examples of datasets included. It distinguishes this tool from siblings like deepghs_list_models and deepghs_list_spaces by focusing specifically on datasets rather than other HuggingFace resources.

  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 provides clear context about what types of datasets are available (Danbooru2024, Sankaku, etc.), helping users understand when this tool is appropriate. However, it doesn't explicitly state when to use alternatives like deepghs_find_character_dataset or deepghs_search_tags, nor does it provide exclusion criteria for when not to use this tool.

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

• deepghs_list_modelsA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds valuable context beyond annotations by specifying the source (HuggingFace), the organization (DeepGHS), and the return format details (paginated list with task type, download counts, likes, and links), enhancing behavioral understanding without contradictions.

  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?

  The description is appropriately sized and front-loaded with the core purpose in the first sentence. The Args and Returns sections are structured clearly, though the list of model types adds some bulk; overall, it remains efficient with minimal waste.

  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?

  Given the tool's moderate complexity, rich annotations, and an output schema (implied by Returns section), the description is complete. It covers purpose, parameters, return values, and context, leaving no significant gaps for agent understanding.

  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 0%, so the description carries full burden. It effectively adds meaning by explaining each parameter in the Args section with examples and defaults (e.g., search keyword filters, sort options, limit range, pagination offset, response format choices), compensating well for the lack of schema 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 clearly states the verb 'List' and resource 'all public models from the DeepGHS organization on HuggingFace,' making the purpose specific. It distinguishes from siblings by focusing on models rather than datasets, spaces, tags, or other resources, and provides examples of included model types like CCIP and WD Tagger Enhanced.

  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 implies usage for listing models with filtering and pagination, but does not explicitly state when to use this tool versus alternatives like deepghs_list_datasets or deepghs_list_spaces. It provides context by listing model types, which helps identify relevant use cases, but lacks explicit exclusions or named alternatives.

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

• deepghs_list_spacesA
  4.4/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds valuable context beyond this by specifying that these are 'public Spaces (live demo apps)' and listing concrete examples of what they include. It also mentions the return format details (SDK type, likes, update dates, direct links), which isn't covered by annotations.

  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?

  The description is well-structured with a clear purpose statement, examples, and parameter/return sections. It's appropriately sized for the tool's complexity. The only minor improvement would be to integrate the examples more seamlessly rather than as a separate bulleted list.

  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?

  Given the tool's moderate complexity, rich annotations, and the presence of an output schema, the description is complete. It covers purpose, examples, parameters, and return format. The output schema handles return value details, so the description doesn't need to duplicate that information.

  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 0%, so the description carries full burden. It provides clear explanations for all three parameters (search, limit, response_format) with examples and constraints. The only minor gap is that it doesn't explicitly mention the default values that are documented 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 the specific action ('List all public Spaces') and resource ('from the DeepGHS organization on HuggingFace'), with examples of what these spaces include. It distinguishes this tool from siblings like 'deepghs_list_datasets' and 'deepghs_list_models' by focusing specifically on Spaces/live demo apps rather than datasets or models.

  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 provides clear context about what types of Spaces are included (reverse image search, Danbooru character lookup, etc.), which helps the agent understand when this tool is appropriate. However, it doesn't explicitly state when to use alternatives like 'deepghs_list_datasets' or 'deepghs_list_models', nor does it provide exclusion criteria.

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

• deepghs_generate_cheesechaser_scriptA
  4.5/5.0
  Behavior4/5

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

  Annotations indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false, covering safety and idempotency. The description adds useful context beyond annotations: it explains that cheesechaser avoids downloading multi-GB tar files, extracts only specified images, and provides efficiency benefits for large datasets. It doesn't contradict annotations, as generating a script is a read-only, non-destructive action.

  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 and front-loaded: it starts with the core purpose, explains cheesechaser, provides usage context with examples, lists parameters clearly, and describes the return value. Every sentence adds value without redundancy, making it efficient and easy to scan.

  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?

  Given the tool's complexity (generating a download script for large datasets), the description is complete. It covers purpose, usage, parameters, and return value (a script with guidance). With annotations providing safety info and an output schema present (implied by 'Returns' section), no critical gaps remain. It effectively guides an agent in selecting and using this 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 0%, but the description includes an 'Args' section that details all parameters (repo_id, output_dir, post_ids, max_workers) with examples and constraints (e.g., '1–16, default: 4'). This compensates for the lack of schema descriptions. However, it doesn't add significant meaning beyond what's implied by parameter names and basic info, so it meets the baseline for adequate 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 purpose: 'Generate a cheesechaser Python script to download images from an indexed DeepGHS dataset.' It specifies the verb ('Generate'), resource ('cheesechaser Python script'), and distinguishes from siblings by focusing on script generation rather than dataset listing, searching, or other operations. The description also explains what cheesechaser does, adding valuable context.

  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 provides explicit guidance on when to use this tool: 'This is the most efficient way to get specific images from datasets like...' It lists example datasets (e.g., deepghs/danbooru2024) and contrasts with downloading entire tar files. It also mentions alternatives implicitly by describing cheesechaser's selective download capability versus bulk downloads, though it doesn't name specific sibling tools as alternatives.

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

• deepghs_generate_waifuc_scriptA
  4.6/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds valuable behavioral context beyond annotations by detailing the 9-step pipeline (crawling, filtering, cropping, etc.), crop size specifications by model format, and the script's purpose for LoRA training quality. This significantly enhances understanding without contradicting 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 well-structured and front-loaded with the core purpose, followed by detailed pipeline steps, crop size specifications, and parameter documentation. Every sentence adds value - no redundant information. It efficiently communicates complex functionality in a digestible format.

  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?

  Given the tool's complexity (9-step pipeline, multiple parameters, model format variations) and the existence of an output schema (returns a string script), the description provides comprehensive context. It explains the full pipeline, parameter meanings, crop specifications, and output format, making it complete enough for an agent to understand and use the tool effectively.

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

  Parameters5/5

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

  With 0% schema description coverage, the description carries the full burden of parameter documentation. It provides detailed parameter semantics in the 'Args' section, explaining each parameter's purpose, format examples, and requirements (e.g., 'character_name' for display, 'pixiv_token' required for Pixiv source). This fully compensates for the schema's lack of 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 clearly states the tool's purpose: 'Generate a ready-to-run waifuc Python script to crawl and clean anime character images for LoRA training.' It specifies the exact action (generate script), resource (waifuc Python script), and distinguishes from siblings by focusing on script generation rather than dataset finding, repo info, or other operations.

  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 provides clear context for when to use this tool (for LoRA training data preparation) and implicitly distinguishes it from siblings like 'deepghs_find_character_dataset' (which finds existing datasets rather than generating collection scripts). However, it doesn't explicitly state when NOT to use this tool or name specific alternatives, keeping it at a 4.

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

• deepghs_search_tagsA
  4.6/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true. The description adds valuable context about the dataset scope (2.5M+ tags across 18 platforms), the normalization problem it solves, and clarifies it returns HuggingFace dataset info with query guidance rather than direct database access.

  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?

  Well-structured with clear sections (overview, problem context, Args, Returns, Note). While somewhat detailed, every sentence adds value: dataset scope, normalization examples, parameter explanations, return format, and usage boundaries. Could be slightly more concise but remains efficient.

  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?

  Given the tool's complexity (cross-platform tag mapping), rich annotations, and output schema, the description provides complete context. It explains the dataset scope, normalization problem, parameter usage, return format, and appropriate usage boundaries. The Note section adds important implementation guidance.

  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?

  With 0% schema description coverage, the description carries full burden. It effectively explains both parameters: 'tag' accepts any format/language/platform with examples, and 'response_format' specifies 'markdown' or 'json' with default behavior implied. The Args and Returns sections provide clear semantic meaning beyond the bare 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 the tool searches the DeepGHS site_tags dataset for cross-platform anime tag normalization, specifying it covers 2.5M+ tags across 18 platforms. It explicitly distinguishes this from sibling tools by focusing on tag mapping rather than character datasets, scripts, or repository listings.

  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 provides explicit guidance on when to use this tool ('key tool for the MultiBoru tag normalization problem') and when to use alternatives ('For programmatic tag lookup at scale, use the dataset's Parquet or SQLite files directly'). It clearly positions this as the reference tool for cross-platform tag mapping.

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

• deepghs_find_character_datasetA
  4.7/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and behavior. The description adds valuable context beyond annotations: it explains the data sources (deepghs and CyberHarem), the automation pipeline details for CyberHarem, and the fallback behavior (suggests waifuc script generation). It doesn't contradict annotations, but could mention rate limits or authentication needs.

  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 and front-loaded with the core purpose in the first sentence. Each subsequent sentence adds specific value: data sources, automation details, parameter explanations, and return behavior. There is no wasted text, and the bullet-point format for Args and Returns enhances readability without verbosity.

  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?

  Given the tool's complexity (search across namespaces with fallback), rich annotations (covering safety and behavior), and the presence of an output schema, the description is complete. It explains what the tool does, when to use it, parameter meanings, and return behavior, including the fallback suggestion. No gaps remain for agent understanding.

  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 0%, so the description must compensate. It provides clear semantics for both parameters: 'character_name (str): Character name to search for (e.g. 'Rem', 'Hatsune Miku')' and 'response_format (ResponseFormat): 'markdown' or 'json''. It also explains the purpose of character_name ('to search for') and the effect of response_format on output format. However, it doesn't detail constraints like maxLength for character_name.

  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 purpose: 'Search for pre-built character image datasets for LoRA training on HuggingFace.' It specifies the verb ('search'), resource ('pre-built character image datasets'), and context ('for LoRA training on HuggingFace'). It also distinguishes from siblings by mentioning specific namespaces (deepghs and CyberHarem) and contrasts with waifuc script generation 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 provides explicit usage guidance: 'Searches both deepghs (BangumiBase) and CyberHarem namespaces for datasets built around a specific character.' It explains when to use it ('saving you from having to run waifuc yourself') and mentions an alternative action ('suggests waifuc script generation if no pre-built dataset is found'), clearly differentiating from sibling tools like deepghs_generate_waifuc_script.

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

• deepghs_get_repo_infoA
  4.7/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, covering safety and idempotency. The description adds valuable context beyond annotations: it explains the tool's purpose for pre-download evaluation and mentions the generated download command, which enhances behavioral understanding without contradicting 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 well-structured and front-loaded with the core purpose, followed by usage guidance and parameter/return details. Every sentence adds value without redundancy, and the inclusion of a schema example is concise and informative, making it efficient for an AI agent to parse.

  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?

  Given the tool's complexity (metadata retrieval with file trees), the description is complete: it covers purpose, usage, parameters, and returns, with an output schema provided. Annotations handle safety and idempotency, and the description adds practical context like the download command, making it fully adequate for agent use.

  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 0%, so the description must compensate. It provides meaningful context for parameters: repo_id is explained with an example, repo_type lists valid values, and response_format specifies options. However, it doesn't detail default values or constraints beyond what's implied, leaving some gaps compared to full schema documentation.

  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 purpose with specific verbs ('Get detailed metadata') and resources ('DeepGHS dataset, model, or space'), distinguishing it from sibling tools like list_datasets or search_tags which have different scopes. It explicitly mentions what information is returned, making 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 Guidelines5/5

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

  The description provides explicit guidance on when to use this tool ('Use this before deciding to download') and distinguishes it from alternatives by highlighting its unique file tree feature. It also implies when not to use it (e.g., for listing or searching instead of getting detailed info), making usage context clear.

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