Server Quality Checklist

Tool Scores

• upload_mediaA
  4/5.0
  Behavior3/5

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

  Since no annotations are provided, the description carries the burden of disclosing behavior. It explains the upload action, the returned mediaId, and file size restrictions, but lacks details on authentication requirements, failure behavior, or idempotency.

  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 primary action and outcome, followed by constraints. Every sentence provides value and there is no redundancy or 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 simple upload tool with complete schema coverage and no output schema, the description covers the essential context: when to use it, what it returns, and what constraints apply. It could mention error scenarios, but overall it is sufficiently complete.

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

  Parameters3/5

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

  Schema description coverage is 100% for the two parameters, so the schema already documents them sufficiently. The description adds file type and size constraints, which are helpful but not necessary for understanding individual 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 clearly states the tool's function: 'Upload a local media file to DingTalk and get a mediaId.' It uses a specific verb ('Upload') and resource ('media file'), and distinguishes it from sibling tools that send 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 explicitly states when to use the tool: 'Required before sending image, file, audio, or video messages.' It also provides file type and size limits, giving clear context for usage. However, it does not explicitly reference sibling tools or state when not to use it.

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

• send_group_messageA
  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 discloses a key behavioral dependency: media types require upload_media to obtain a mediaId. However, it does not mention any side effects, required permissions, failure modes, or response format. For a send operation, additional disclosure about potential errors or the nature of the operation (irreversible write) would be valuable.

  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. The first sentence states the action and lists capabilities; the second provides an essential prerequisite. There is no redundancy or filler; every sentence 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 21 parameters and conditional logic, the description covers the core message types and the upload prerequisite. It doesn't explain actionCard button configurations or parameter interdependencies, but those are already detailed in the schema. The lack of an output schema means a note about the return value would be helpful, but it is not a critical gap.

  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 has 100% parameter coverage with detailed descriptions, so the baseline is 3. The description adds value by explaining the mediaId prerequisite for image/file/audio/video, which clarifies the origin of several parameters. It also succinctly enumerates message types, helping agents understand how to pick the right msgtype and corresponding fields.

  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 action: 'Send a message to a DingTalk group chat.' It lists supported message types (text, markdown, image, link, actionCard, file, audio, video), which specifies the scope. The mention of 'group chat' distinguishes it from sibling send_single_message, and the reference to upload_media as a prerequisite clarifies its purpose.

  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 sending messages to a DingTalk group chat. It also gives an explicit usage prerequisite: 'Use upload_media first for image/file/audio/video to get a mediaId.' While it doesn't explicitly state when not to use it (e.g., for single messages), the group-chat framing and sibling names imply the boundary.

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

• send_single_messageA
  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 of behavioral disclosure. It discloses that recipient arrays are merged and deduplicated, that the call is a single batch operation, and that duplicate name matches cause the entire batch to fail. This goes beyond the bare operation and gives critical operational insight, though it omits details like return responses or error handling.

  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 and front-loaded with the core purpose, followed by recipient behavior and a concrete prerequisite. Every sentence carries essential information; there is no filler or repetition of schema enum values.

  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 has 22 parameters, no output schema, and no annotations, the description covers the most critical operational context: batch semantics, deduplication, max recipients, name-match failure mode, and the upload_media prerequisite. It lacks explicit return value or error code information, but for such a many-parameter tool it is remarkably complete and actionable.

  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 the baseline is 3, but the description adds meaningful cross-parameter semantics: it explains the relationship between userIds and userName (merged, deduplicated, max 20), states that media types require a mediaId from upload_media, and clarifies that userName matches must be exact. This adds value beyond the individual schema field 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 sends a message to DingTalk users, enumerates supported message types, and specifies recipient resolution via userIds and userName. It distinguishes itself from the sibling send_group_message by focusing on user-targeted (not group) messaging and details the max 20 recipient batch behavior.

  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 explicit guidance on when to use upload_media first for media types, and heavily documents recipient constraints (max 20, exact name search, duplicate handling). It does not explicitly contrast with send_group_message, but the tool name and description imply direct-user versus group context, making the usage intent clear.

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