Server Quality Checklist

Tool Scores

• wechat_official_list_published_articlesA
  3.8/5.0
  Behavior4/5

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

  While annotations already indicate read-only and idempotent behavior, the description adds a meaningful scoping constraint—'reads the account's own publication history; not an arbitrary third-party account crawler.' This goes beyond annotations by clarifying what the tool cannot do, though it omits pagination and result format details.

  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 concise sentences, with the primary purpose front-loaded and the scope clarification in the second sentence. No wasted words or redundancy.

  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?

  For a read-only list tool with 4 parameters and no output schema, the description adequately covers purpose and scope but lacks explicit details about return format, pagination behavior, or search matching semantics. The schema provides parameter defaults, but the description could be more complete about what the returned list contains.

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

  Parameters1/5

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

  Schema description coverage is only 25% (only 'query' has a description). The tool description adds no parameter-specific explanations for limit, offset, or response_format; it merely paraphrases the 'search' aspect already covered by the schema's query description. This does not compensate for the low 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 lists or searches articles published by the currently logged-in account, distinguishing it from arbitrary third-party crawling. This specific verb+resource+scope clarifies its role and separates it from siblings like read_article or report tools.

  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: it operates on the account's own publication history, not third-party accounts, implying when to use it. However, it does not explicitly mention alternatives or exclusion criteria, such as using wechat_official_read_article for a single article.

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

• wechat_official_read_articleA
  3.9/5.0
  Behavior4/5

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

  The description adds significant behavioral detail beyond the annotations: it explains the anonymous-first request, the authentication preflight, and the conditional fallback to Cookie-based auth. This complements the readOnlyHint and idempotentHint. No contradiction with 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?

  Two sentences with no fluff: the first sentence front-loads the primary purpose and deliverables, the second adds a critical behavioral nuance. Every word earns its place.

  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 core functionality and auth behavior are covered, but without an output schema, the description does not describe return-value structure, truncation behavior, or error handling. It is adequate for a read-only tool but leaves some ambiguity.

  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 only 25% (only 'authentication' has a schema description). The description elaborates on the authentication parameter's default behavior, but does not explain max_characters or response_format, leaving them partially ambiguous despite their enums and defaults.

  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 a specific action verb ('Extract') and identifies the exact resource ('one public mp.weixin.qq.com/s article URL'), while enumerating the extracted fields (title, account, author, etc.). This distinguishes it from sibling tools like wechat_official_list_published_articles (listing) and wechat_official_get_article_report (analytics).

  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 usage context is implied by the name and description (reading a single article), but there is no explicit 'use when' or 'use instead' statement referencing sibling tools. No exclusions or alternative tool recommendations are provided.

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

• wechat_official_get_follower_reportA
  4/5.0
  Behavior4/5

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

  Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context: it reads 'official exported' data (not real-time computation), enforces a maximum 100-day range, and returns raw source columns. These details go beyond what annotations provide, though pagination and error behavior are not disclosed.

  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 consists of two concise, front-loaded sentences with no redundant information. Every clause adds value: the source, the scope, the date limit, and the return behavior.

  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 description is fairly complete given the absence of an output schema and the moderate complexity (5 params, 2 required). It covers the core purpose, the constraint on date range, and the raw nature of the return data. However, it does not clarify pagination behavior or available output formats, which would be more helpful for an agent.

  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?

  With only 40% schema description coverage, the description partially compensates by adding the 'at most 100 days' constraint relevant to begin_date/end_date. However, it does not explain limit, offset, or response_format, which remain undocumented in the schema and description. The enum and constraints for these params are present in the schema, but the description adds limited meaning beyond the date parameters.

  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 a specific verb ('Read') and clearly identifies the resource: 'currently logged-in account's official exported follower analytics.' It also adds a key scope ('fixed date range of at most 100 days') and distinguishes from sibling analytics tools by focusing on follower data and noting it returns source columns as supplied by WeChat.

  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 when follower analytics are needed, but it does not explicitly state when to use this tool versus alternatives like get_article_report. The mention of the 100-day date range constraint is a guideline, but no exclusions or alternative tool names are provided.

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

• wechat_official_get_account_infoA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds a valuable behavioral detail not covered by annotations: the tool does not expose cookies or login tokens. This provides security context beyond the 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 two sentences, front-loaded with the action and fields. It is concise, with no fluff, and every sentence adds value. 'Does not expose cookies or login tokens' is a useful caveat in one short sentence.

  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 read-only tool with no output schema, the description adequately explains what is returned (the four listed fields) and a key limitation (no tokens). It does not explain response_format variants, but the schema covers the enum/default. Overall, it is complete for a tool of this complexity.

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

  Parameters2/5

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

  The input schema has one parameter (response_format) with 0% schema description coverage, so the description should compensate. However, it never mentions the parameter or its effect on output format. The schema's enum and default provide some meaning, but the description adds no parameter semantics.

  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 action ('Read') and resource (the currently logged-in WeChat Official Account's nickname, original ID, avatar, and account type). It distinguishes this tool from siblings such as article or report tools, which are about different 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: it is for reading info about the logged-in account. It implies usage when account details are needed, though it does not explicitly list alternatives or when not to use the tool. The 'currently logged-in' phrase adds scope clarity.

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

• wechat_official_check_authA
  4.2/5.0
  Behavior4/5

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

  Annotations already cover read-only, open-world, idempotent, and non-destructive behavior. The description adds meaningful context beyond annotations: the cookie is locally stored, only non-secret status is returned, and cookies must not be passed as arguments. This clarifies the tool's security and privacy posture.

  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 short sentences, front-loaded with the main verb and purpose, and contains no fluff. Every sentence earns its place: purpose, when to call, and a critical security warning.

  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 auth-check tool with rich annotations, the description is mostly complete: it states what is validated, what is returned, when to call it, and a key constraint. The only minor omission is what an invalid/expired cookie returns, but the high-level return description and the tool's straightforward nature keep this sufficient.

  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?

  The single optional response_format parameter is fully described by the schema with an enum and default value, so the agent can invoke the tool correctly without additional description. However, the description does not mention this parameter at all, giving 0% schema description coverage; since the parameter is trivial and optional, this is not a serious gap.

  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 validates a locally stored WeChat cookie and returns non-secret session/account status. This distinguishes it from sibling tools that read articles, reports, or account info, making it a dedicated auth preflight check.

  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 'Call this first before backend reads,' providing clear when-to-use guidance. The warning 'Never pass a cookie as an argument' is a useful negative instruction, though it does not name alternative tools because none exist for this purpose.

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

• wechat_official_get_article_reportA
  4.2/5.0
  Behavior4/5

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

  The description adds useful behavioral detail beyond the annotations: the date-range limit of 100 days and the guarantee that it returns only WeChat's original columns without inventing metrics. This complements the read-only and non-destructive hints already provided.

  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 deliver the core purpose and a key behavioral guarantee with no fluff. The description is front-loaded and every clause earns its place.

  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 tool with five parameters, no output schema, and strong annotations, the description covers the essential context: what the tool does, the date-range limit, and the return behavior. It lacks mention of pagination or response_format options, but the schema provides those details, so the description is sufficient for selection and basic 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?

  The description adds a meaningful constraint on begin_date/end_date by noting the maximum range of 100 days, which is not in the schema. However, it does not elaborate on limit, offset, or response_format, leaving those parameters to be understood from defaults and naming. Schema coverage for these parameters is low (40%), so the description only partially compensates.

  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 reads the currently logged-in account's official exported article analytics, using a specific verb ('read') and a well-defined resource. It also distinguishes from siblings by focusing on article analytics as opposed to follower reports or article content.

  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 by specifying the scope (current account, fixed date range up to 100 days) and the nature of the data (exported article analytics). However, it does not explicitly mention alternatives or exclusions, though the sibling tool names imply distinct use cases.

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

• wechat_official_create_draftA
  4.4/5.0
  Behavior4/5

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

  Annotations only signal that the tool is not read-only, not idempotent, and not destructive. The description adds meaningful behavior: 'The draft is saved but never published' and 'Requires confirm=true', which are not captured in annotations. It could add more about auth or error behavior, but the added context suffices.

  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 four short, purposeful sentences. Each sentence adds distinct information: purpose, dependency, requirement, and outcome. There is no wordiness or 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?

  The description covers the core workflow: prerequisites (cover media IDs), the safety mechanism (confirm=true), the limit (8 articles), and the outcome (saved draft, not published). It does not mention return values or error handling, but given no output schema and a straightforward creation operation, this is reasonably complete.

  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 67%, so the description partially compensates. 'Uses cover media IDs from prior uploads' adds meaning to the cover_media_id parameter by explaining its source, and 'Requires confirm=true' clarifies the confirm safety gate. However, response_format remains undocumented, so it does not fully compensate for all gaps.

  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 ('Create and save'), the resource ('draft'), and the scope ('up to 8 articles', 'logged-in WeChat Official Account'). It also distinguishes from siblings by emphasizing the draft is never published, separating it from publishing or reading tools.

  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: it requires cover media IDs from prior uploads and confirm=true, indicating this is used after uploading images and before publication. It does not explicitly name alternative tools or when not to use, but the workflow is implied.

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

• wechat_official_validate_draftA
  4.6/5.0
  Behavior5/5

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

  Annotations (readOnlyHint, idempotentHint, destructiveHint) already indicate a safe read operation, but the description adds critical behavioral context: it is local-only, does not access the network, and returns errors/warnings/summaries. It also specifies exactly what validation is performed, going beyond the structured 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?

  Three concise, front-loaded sentences. The first sentence states purpose and scope, the second details checks, the third covers output and network behavior. Every sentence earns its place with no 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 validation tool with two parameters (one being a rich array), the description covers the key aspects: what is validated, that it is local-only, and what it returns. It does not detail the return format, but the response_format parameter handles that. The absence of an output schema makes the description's mention of 'errors, warnings, and per-article summaries' essential and sufficient for an agent to understand the tool's behavior.

  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 description explains which fields are validated (title, author, digest, content_html, cover_media_id), adding meaning beyond the schema. However, it does not mention the response_format parameter or cover boolean fields like show_cover/open_comment, which the schema does describe. With 50% schema coverage, the description partially compensates but could go further.

  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 a specific verb (validate), names the resource (article drafts), and lists concrete actions (checks lengths, forbidden tags/URLs, cover media IDs). It clearly distinguishes itself from sibling tools like create_draft or read_article by focusing on validation rather than mutation or retrieval.

  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 title 'Validate a draft before saving' and description 'Local-only validation' clearly imply use before saving a draft, especially compared to wechat_official_create_draft. No explicit 'use this when' or 'instead of X' is stated, but the context is strong enough for an agent to infer the intended scenario.

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

• wechat_official_upload_imageA
  4.7/5.0
  Behavior5/5

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

  The description goes beyond annotations by disclosing that the tool requires confirm=true, returns only safe metadata (filename, size, MIME, media_id, CDN URL), and never publishes content. It also implies the need for a logged-in account. These details provide meaningful behavioral context beyond the readOnlyHint/idempotentHint/destructiveHint annotations, with no contradiction.

  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 with the verb and resource front-loaded. Each sentence earns its place: formats, usage modes, safe response, confirmation requirement, and a non-publication guarantee. No redundant or filler content.

  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 and the presence of annotations and a well-described schema, the description covers all essential aspects: what it uploads, accepted formats, usage modes, the confirm gate, safe return metadata, and the non-publication guarantee. The file path root restriction is in the schema, so no critical information is missing.

  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 75%, and the description adds additional meaning for key parameters: file_path is clarified as a local image with specific allowed formats, usage is mapped to 'material (cover)' or 'article body image,' and confirm is highlighted as mandatory. The response_format parameter is not mentioned in the description, but the schema already describes its enum values and default, so the overall parameter semantics are well-supported.

  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 uploads a local image file to the logged-in WeChat Official Account, and specifies the image formats (JPEG, PNG, GIF) and the two usage modes (material or article body). This distinguishes it from sibling tools that handle reading, reports, and drafts. It also explicitly notes 'Never publishes,' setting it apart from publication actions.

  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 context on when to use the tool: for uploading local images as cover or inline article images, and notes the requirement confirm=true. It does not explicitly name alternative tools for other scenarios (e.g., reading or publishing), but the purpose clarity and 'Never publishes' provide strong implicit differentiation.

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