Server Quality Checklist

Tool Scores

• import_sourceA
  3.6/5.0
  Behavior2/5

  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 the return value (raw_markdown and metadata) but fails to mention any side effects, permissions, or error conditions (e.g., what happens if URL is unreachable or file not found). This is insufficient for a clear behavioral understanding.

  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 extremely concise, comprising two short sentences. The first sentence states the purpose and input, the second defines the output. No unnecessary words, and key 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 the tool's low complexity (3 parameters, no nested objects) and lack of an output schema, the description adequately covers input and output. It mentions both local files and URLs, and specifies the return type. Minor gap: no guidance on mutual exclusivity of parameters (url/path) beyond the schema's 'required' field.

  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 all parameters documented in the input schema. The description merely restates the source types without adding new meaning or constraints, matching the baseline score per the rubric.

  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 explicitly states the verb 'import' and resource 'original content (local markdown file or URL webpage)', distinguishing it from sibling tools (estimate_originality, transform_for_wechat, save_to_wechat_draft) which handle estimation, transformation, or saving.

  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 implies usage for preparing content for WeChat public account processing, which indirectly suggests when to use it (before transformation/saving). However, it does not explicitly state when not to use it or mention alternatives among siblings, providing only minimal guidance.

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

• transform_for_wechatA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description must fully disclose behavior. It lists key automatic processes (paragraph splitting, code handling, etc.) but omits details like whether the transformation is reversible, what happens with unsupported markdown, or error handling. Adequate but not comprehensive.

  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 single-sentence description packs multiple features efficiently. While it could be broken into bullet points for clarity, it is front-loaded with the primary action and free of fluff. Minor deduction for dense structure that might be harder to parse.

  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 complexity (multiple automatic steps) and no output schema, the description covers core behaviors well. It mentions title candidates, templates, and specific markdown conversions. Lacks details on edge cases (e.g., images, tables) but sufficient for general 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 coverage is 100%, so description adds value beyond field names. It explains that 'title' influences title candidates and 'apply_template' controls header/footer templates. This contextualizes the parameters' roles in the transformation, justifying a score above baseline.

  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 converts markdown to WeChat-optimized HTML, listing specific transformations (paragraph splitting, code blocks, hyperlinks to footnotes, templates, title candidates). This distinguishes it from siblings that likely handle different stages like importing or saving.

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

  Usage Guidelines2/5

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

  No guidance on when to use this tool versus siblings like 'import_source' or 'save_to_wechat_draft'. The description does not specify prerequisites, exclusions, or alternative tools, leaving the agent without context for selection.

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

• estimate_originalityA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description must fully explain behavior. It discloses that the tool compares against the user's own draft history and is not official. However, it does not mention whether the tool is read-only, any required permissions, rate limits, or what happens if history is empty. This leaves some behavioral 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 extremely concise: two sentences in Chinese that capture purpose, scope, and limitation. No redundant information. Every sentence adds value.

  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 has few parameters and no output schema. The description explains what it does and its limitations but omits details about the return format (e.g., score, label) and how the result can be used. Given the simplicity, it is minimally adequate but not rich.

  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 both parameters described. The description adds no new semantic information beyond the schema; it only restates concepts already present (e.g., comparing against history). Therefore, the standard baseline of 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 tool name 'estimate_originality' is self-explanatory, and the description clearly states it assesses originality of content to assist in deciding whether to mark as 'original'. It distinguishes from official WeChat check and implies a scope limited to user's own drafts, which differentiates it from sibling tools like import_source or save_to_wechat_draft.

  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: this is a self-assessment for marking content as original, based on user's draft history. It explicitly warns that it cannot replace WeChat's official plagiarism check, giving a clear limitation. However, it does not directly compare with alternative tools among siblings, though siblings perform different functions.

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

• save_to_wechat_draftA
  4.4/5.0
  Behavior4/5

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

  With no annotations, description clearly states the tool only saves as draft and never auto-publishes, which is critical for agent decisions. No mention of side effects or failure modes, but core behavior is well covered.

  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, no redundancy. Efficiently conveys purpose, constraint, and post-action step.

  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 output schema, description adequately covers key behaviors for a 9-parameter tool. Could mention expected success feedback or error handling, but sufficient for core usage.

  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% with all parameters described. The description adds value by linking html_content to transform_for_wechat output, providing workflow context beyond 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?

  Explicitly states it saves processed content to WeChat draft box, distinguishing from siblings (estimate_originality, import_source, transform_for_wechat) which handle earlier stages. Emphasizes it only creates drafts, not auto-publish.

  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?

  Indicates when to use (after processing) and what not to expect (no auto-publish). Could be more explicit about prerequisites or when not to use, but context with siblings implies it's the final step.

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