Server Quality Checklist

Tool Scores

• send_stickerA
  4.1/5.0
  Behavior1/5

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

  The description discloses the random-selection behavior and stickerId override, but it directly contradicts the readOnlyHint=true annotation by describing a 'send' operation, which is an action with side effects. This is a clear annotation contradiction, so the score is 1.

  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 compact yet comprehensive, front-loading the purpose and then giving usage notes. Every sentence adds practical value without redundancy.

  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?

  The tool is simple with two well-documented parameters, and an output schema exists. The description covers preparation (listing stickers), selection strategy, and fallback behavior, making it adequately complete for an agent to use correctly.

  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 covers both parameters with descriptions. The description adds value by explaining how to pick query based on conversation mood, and the behavior when multiple stickers match. This goes beyond the schema, so a score of 4 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 description clearly states 'Send an expressive sticker (meme/表情包) that renders as an image in the chat' — a specific verb and resource. It also distinguishes itself from siblings like list_available_stickers and add_sticker by focusing on sending in chat.

  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?

  It explicitly says 'Use this proactively whenever a sticker would make the reply more fun or expressive' and provides examples of when to use. It also instructs to call list_available_stickers first if the library hasn't been seen, giving clear guidance.

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

• add_sticker_by_pathA
  4.6/5.0
  Behavior4/5

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

  Annotations already declare non-read-only and non-destructive, so the description adds useful context: local mode restriction, supported file formats, and max size. This goes beyond annotations and clarifies operational constraints.

  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 sentences, each earning its place. Front-loaded with the verb and purpose, immediately followed by usage guidance and technical constraints. No filler.

  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 simple tool (3 flat parameters, no output schema, no nested objects), the description provides essential context: local-only operation, file type and size limits. It doesn't describe post-conditions or error behavior, but that's not necessary for this straightforward create operation.

  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 already covers all parameters with descriptions, so baseline is 3. The description enhances filePath semantics by adding supported formats (png/jpeg/gif/webp/avif) and max size (8MB), which are not in the schema. This adds real value.

  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?

  Clearly states the action 'Add a new sticker from an image file on this computer', specifying the resource (sticker) and source (local path). It distinguishes itself from siblings like add_sticker or create_sticker_upload by emphasizing 'local/stdio mode only' and 'by path'.

  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?

  Explicitly says 'Use when the user gives a local file path' and adds 'local/stdio mode only', providing a clear condition for when to use this tool instead of alternatives. This is excellent guidance.

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

• add_stickerA
  4.7/5.0
  Behavior4/5

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

  Annotations indicate this is a write operation (readOnlyHint=false) and non-idempotent, which the description aligns with. The description adds valuable context: URL restrictions, supported formats (png/jpeg/gif/webp/avif), max 8MB file size, and guidance on how to name and tag. This goes beyond the schema and annotations, though it doesn't address failure modes or duplicate names.

  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 longer than average but every sentence delivers critical instructions: source restrictions, alternative tool, naming strategy, and supported formats. It is front-loaded with the core purpose and then systematically covers constraints and usage, with no redundancy or filler.

  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 and the presence of an output schema, the description is remarkably complete. It covers the essential context for correct use: what input is allowed, what to do if the image is a file, how to choose name/tags, format limits, and explicit exclusions. The presence of an output schema means return values don't need explanation, so this is fully adequate.

  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 100%, so parameters are already well-documented. The description adds meaningful context beyond the schema: the imageUrl parameter's restriction to public http(s) URLs and explicit prohibition of data:image/base64, plus format and size limits. It also provides strategy for name and emotions parameters (short name, 1-8 tags, use user description if available).

  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: 'Add an image to the sticker library from an existing public http(s) image URL only.' It specifies the verb (Add), resource (sticker library), and crucial scope (public URL only), effectively distinguishing it from siblings like create_sticker_upload and add_sticker_by_path.

  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 when-to-use and when-not-to-use guidance: it warns against data:image/base64, third-party hosts, and directs users with attached image files to create_sticker_upload instead. It also advises on naming and tag selection, instructing to use the user's description to avoid unnecessary visual analysis.

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

• list_available_stickersA
  4.7/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true. The description adds behavioral context by specifying that it lists *every* sticker, the included fields, and that results should be used to know which moods can be expressed. 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 redundancy: the first sentence states the tool's purpose, the second gives usage context. Front-loaded and 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?

  For a zero-parameter, read-only listing tool, the description fully specifies what is listed, when to call it, and how it feeds into subsequent actions. No output schema exists, but the description mentions the key output fields, making it 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?

  The tool has zero parameters, so the schema fully covers parameter semantics (baseline 4). The description adds value by explaining what data is returned and how it relates to sending stickers, though no parameter-specific info is needed.

  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 the verb 'List' with a specific resource ('every sticker in the library') and names the output fields ('id, name and emotion/scene tags'), clearly stating the action and result. It distinguishes from siblings like send_sticker, which sends, and add_sticker, which adds.

  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?

  It gives explicit when-to-use guidance: 'Call this once early in a conversation (or when send_sticker reports no match)' and then instructs 'afterwards you can call send_sticker directly'. This also clarifies the alternative tool.

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

• create_sticker_uploadA
  4.9/5.0
  Behavior5/5

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

  Despite annotations indicating a write operation (readOnlyHint=false), the description goes far beyond them with actionable behavior: URL expires in 10 minutes, upload via HTTP PUT with specific content types, sticker saved as soon as PUT succeeds, and step-by-step upload workflow. This provides exceptional transparency for the agent.

  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 moderately long but every sentence carries essential information for correct usage. It front-loads the primary action, then follows a logical sequence (how to upload, what not to do, how to fill parameters, expiration). Nothing feels redundant or wasted.

  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?

  For a tool with no output schema, the description covers all necessary context: the one-time URL, the required HTTP PUT call, content types, the fact that no further tool calls are needed, and the 10-minute expiry. The description is self-sufficient for an agent to invoke and complete the workflow correctly.

  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 clear parameter descriptions, so baseline is 3. The description adds extra semantic guidance by explaining how to populate the name and emotions parameters: 'If the user already told you what the image is, skip visual analysis and use that description for the name and tags.' This goes beyond 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 tool's purpose: 'Create a one-time upload URL on this sticker library for the user's attached image bytes/file.' It uses a specific verb and resource, and distinguishes from siblings by specifying 'Use this when adding a sticker from an attachment' and explicitly warning 'do not call add_sticker afterwards.'

  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 when-to-use guidance: 'Use this when adding a sticker from an attachment.' It also gives alternatives (do not upload to third-party hosts, do not curl the MCP endpoint) and exclusions (do not call add_sticker afterwards), making the decision boundary clear.

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