Server Quality Checklist

Tool Scores

• weixin_send_fileB
  3.2/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the source can be a local path or URL but says nothing about side effects, required permissions, or failure behavior, which is a significant gap for a send operation.

  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 sentence that front-loads the action and recipient. It avoids wasted words and is appropriately sized for the tool's simplicity.

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

  Completeness2/5

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

  The tool has no output schema and no annotations, leaving the description to convey essential context. It omits any mention of prerequisites, authentication, or what distinguishes this from weixin_send_image, making it incomplete for safe 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 input schema covers all four parameters with descriptions, achieving 100% coverage. The description only restates the 'source' property's type ('local file path or URL'), adding no new information beyond what the schema already provides, so it merits the baseline score.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Send') and resource ('file attachment') to define the tool's core function. It clearly states what is sent and to whom, and distinguishes itself from sibling tools like weixin_send_image by mentioning generic file attachments. However, it doesn't explicitly contrast with siblings, so it's clear but not fully differentiated.

  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 this tool is used for sending files as attachments, but it does not specify when to choose it over weixin_send_image or weixin_send. There are no exclusion criteria or alternative tool guidance, leaving the agent to infer usage context.

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

• weixin_send_imageA
  3.5/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It conveys the core action and input options, but does not mention permissions, error behavior, return value, or side effects. For a send tool, this is adequate but not rich.

  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 that are front-loaded and direct. Every sentence adds useful information without unnecessary detail or repetition.

  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?

  Given no output schema and no annotations, the description is the primary source of context. It covers the essential operation but lacks information about response format, success/failure indicators, or special handling (e.g., context_token), leaving moderate gaps for a 4-parameter 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 all parameters are documented. The description adds little beyond that—it restates the source type and caption optionality, but doesn't provide additional meaning for 'to' or 'context_token'. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('Send an image') and the recipient ('to a WeChat user'), making the tool's purpose obvious. However, it does not explicitly distinguish this from sibling tools like weixin_send_file, so it doesn't fully meet the 'distinguishes from siblings' criterion.

  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 sending images by specifying source types (local path or URL) and optional caption, giving some context. However, it provides no explicit guidance on when to choose this over weixin_send or weixin_send_file, nor any exclusions or prerequisites.

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

• weixin_sendA
  3.6/5.0
  Behavior2/5

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

  No annotations are provided, leaving the description to disclose behavioral traits. It mentions the conversation-linking behavior of context_token but omits important aspects like permissions, failure modes, or response behavior. For a mutation tool with zero annotation coverage, this is a significant gap.

  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 concise sentences with the main purpose front-loaded and no redundant information. Every word earns its place.

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

  Completeness2/5

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

  There is no output schema, so the description should explain return values or errors. It does not, leaving the agent without guidance on what to expect after sending. The schema is detailed, but the description lacks contextual details about success/failure or post-send behavior.

  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 schema already covers all parameters with 100% description coverage, so the baseline is 3. The description adds no new parameter semantics beyond restating the context_token behavior already described 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 'Send a WeChat text message to a user' with a specific verb and resource. This distinguishes it from sibling tools like weixin_send_image and weixin_send_file, which handle different media types.

  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 for the main use case (sending text) and provides a specific instruction on when to use context_token ('from a received message'). However, it does not explicitly mention alternatives or exclusions, so it doesn't earn a 5.

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

• weixin_get_configA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must cover behavior. It discloses that the config includes the typing_ticket needed for sendTyping, which is useful. However, it does not state whether the operation is read-only, whether authentication is required, or how errors are handled, 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 a single, front-loaded sentence with no filler. It states the action, the key output element, and the recommended call timing, each earning 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 simple config getter with two parameters and no output schema, the description adequately conveys the primary purpose and the important typing_ticket field. It lacks detail on the full return structure or failure modes, but the tool's complexity is low, so a 4 is appropriate.

  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 user_id and context_token. The description mentions 'user' and 'typing_ticket' but does not add semantic detail beyond the schema, so it stays at the baseline of 3.

  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 'Get bot config for a user' with a specific verb and resource, and singles out the typing_ticket purpose. This distinguishes it from sibling tools like weixin_send or weixin_contacts, which handle different 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 phrase 'Call before sending typing indicators' provides explicit timing and context for when the tool should be invoked. It does not mention when not to use it or alternative tools, but the usage context is clear, making it a 4 rather than a 5.

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

• weixin_pollA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses key behaviors: persistent cursor, prevention of re-delivery, and returning new messages since last poll. However, it lacks details on side effects, error handling, or what happens when no new messages are available, 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 sentences long, each conveying essential information: the action, the cursor mechanism, and the output. It is front-loaded with the primary purpose and contains no redundant or filler text.

  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 simple with one parameter and no output schema, so the description provides adequate context for its core function. It explains the cursor persistence and return behavior, but could be slightly more explicit about output format or edge cases, though these are minor for a polling 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 coverage is 100% and the single parameter reset_cursor has a clear description, so the tool description doesn't need to add much. The tool description's mention of a persistent cursor indirectly relates to the parameter but doesn't provide additional meaning beyond what the schema already offers.

  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: polling for new WeChat messages. It uses a specific verb ('Poll') and resource ('WeChat messages') and differentiates from sibling tools like weixin_send or weixin_download by focusing on the retrieval of messages.

  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 its usage through the persistent cursor mechanism, making it clear this is for repeated polling to fetch only new messages. It doesn't explicitly name alternatives or exclusions, but the purpose is clear enough for an agent to choose it over sending or downloading tools.

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

• weixin_downloadA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It adds useful context by explaining that parameters must be extracted from message items (image_item, file_item, video_item), but it does not disclose the return format, potential side effects, or error behavior. This is a moderate level of 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 two sentences long, with the main purpose front-loaded and no redundant information. Every sentence contributes meaning, achieving high conciseness.

  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 2-parameter tool without an output schema, the description covers the core functionality and parameter source. However, it does not mention what the download returns or where it goes, which is a notable gap for download operations. Otherwise, it is complete for the tool's complexity.

  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 schema already provides parameter names and examples, but the description adds important semantics by generalizing the extraction source to image_item, file_item, or video_item, beyond the schema's image-only examples. This enriches the understanding of where to find the values.

  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 ('Download') and resource ('media (image/file/video) from a received message'). It distinguishes the tool from sibling tools like weixin_send and weixin_get_config by specifying the action and source. No ambiguity about what the tool does.

  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 phrase 'from a received message' provides clear context for when to use this tool, differentiating it from send-related siblings. However, it does not explicitly state exclusions or mention alternative tools, so it falls short of a 5.

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

• weixin_contactsA
  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. It clearly indicates this is a read/list operation and discloses the return fields: userId, lastSeen, lastText, contextToken, msgCount. It lacks details like pagination or ordering, but for a simple list tool, it is sufficiently transparent.

  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: first states the purpose, second lists return fields and provides a practical usage hint. No redundant words, front-loaded with the key action.

  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 zero-parameter tool with no output schema, the description covers the essential return values and the next step (using userId in weixin_send). It could mention ordering or that lastSeen is a timestamp, but the information provided is sufficient for most use cases.

  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 input schema has zero parameters, so the baseline is 4. The description adds meaning beyond the schema by explaining the output fields and how to use the resulting userId, which is valuable context.

  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 opens with a specific verb and resource: 'List users who have messaged the bot.' It clearly states the tool's function and differentiates from sibling tools like weixin_send and weixin_poll, which involve sending or polling messages rather than listing contacts.

  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: use this tool to discover users who have messaged the bot, and then use the returned userId as the 'to' parameter in weixin_send. It doesn't explicitly name alternatives or exclusions, but the downstream usage is implied and sufficient for a contact-listing tool.

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