Server Quality Checklist

Tool Scores

• lanhu_get_designsA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds valuable behavioral context beyond annotations: it clarifies that preview_size refers to cover dimensions, not canvas size, and directs that canvas size must be read from Design IR meta.canvas. This helps avoid misuse.

  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—with no extraneous information. It front-loads the purpose and immediately follows with critical behavioral and workflow details. Every sentence contributes meaningfully.

  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 list tool with one parameter and no output schema, the description provides adequate context: purpose, output fields, a behavioral caveat, and follow-up use. It is complete enough for an agent to use correctly in the workflow, though it does not mention potential pagination or other limits.

  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% as the single parameter 'url' has a description. The tool description does not add new information about the parameter beyond what the schema provides, so it meets the baseline without adding extra semantic 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?

  The description clearly states it retrieves a list of UI designs from a Lanhu project, specifying the fields (index, id, name, cover URL, cover size). It distinguishes itself from sibling tools by explicitly positioning itself as the first step and directing subsequent calls to lanhu_get_design_schema or lanhu_get_design_slices using the returned index or id.

  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 marks itself as '[第一步]' (step 1) and instructs the user to use the returned values to call other tools. This provides clear usage context and workflow guidance, though it does not explicitly state when not to use this tool.

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

• lanhu_search_design_nodesA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint. The description adds context about pagination, return fields, and inclusion of hidden nodes, which is valuable 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 a concise two-sentence paragraph that front-loads the purpose and includes key details without redundancy. Every sentence adds value.

  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 what the tool returns, when to use it, and mentions pagination. Without an output schema, it provides a good overview. Could mention support for fuzzy search via query parameter, but overall complete for a search 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 parameters are fully documented. The description does not add per-parameter details but provides overall context that the tool is paginated and returns specific fields, which is baseline sufficient.

  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 that the tool searches a paginated node directory for a single design, returning specific fields (id, path, geometry, copy, DS identity, visible). This distinguishes it from sibling tools like preview, designs, schema, and slices.

  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 to prioritize this tool for large designs or when locating node_ids. It implies alternatives but does not explicitly list when not to use or name other tools.

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

• lanhu_get_design_slicesA
  4.3/5.0
  Behavior4/5

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

  Annotations indicate readOnly and openWorld hints. The description adds value by detailing the returned data (download addresses, sizes, coordinates) and clarifying off_canvas semantics. No contradictions.

  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, front-loaded with essential information. Every word carries weight; no 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?

  Despite no output schema, the description sufficiently explains what the tool returns. Parameter descriptions are complete, and the tool's behavior (including edge case 'off_canvas') is covered. No gaps.

  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%. Both parameters are well-documented in the schema. The description adds no new parameter-level detail beyond the schema, so baseline 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 description clearly states the tool retrieves '切图清单' (slices list) for a single design, listing specific data fields (PNG/SVG URLs, logical_size, position, stored_size). This distinguishes it from siblings like get_design_preview or get_design_schema.

  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 explains the meaning of 'off_canvas=true' and its practical implication ('是否使用以及资源如何落地由目标端决定'). It provides context for interpreting results but does not explicitly contrast with alternatives.

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

• lanhu_get_design_schemaA
  4.5/5.0
  Behavior4/5

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

  Annotations provide readOnlyHint and openWorldHint. The description adds key behavioral context: auto-degradation for large responses, platform-neutral coordinates, and retention of hidden/zero-size nodes in exact mode. 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is structured and front-loaded with the core purpose. It is slightly verbose but every sentence adds necessary detail for correct usage. Some repetition could be trimmed, but overall efficient.

  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?

  Despite no output schema, the description explains what the tool returns (IR including nodes, coordinates, etc.), limitations (auto-degradation, platform-neutral), and how to use different detail modes with node_ids. It also relates to sibling tools.

  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%, baseline 3. The description adds value by explaining detail level purposes, partitioning strategy, and providing URL format examples. It clarifies the design parameter's specification methods (index, uuid, name).

  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 precisely states the tool retrieves Design IR, listing specific data types (node hierarchy, coordinates, text, fonts, colors, shadows, etc.). It distinguishes itself as the primary design info source and references sibling tools for other tasks.

  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?

  Explicit guidance is given for when to use summary vs full vs exact detail levels, including auto-degradation of full responses. It advises using lanhu_search_design_nodes first for node location, then partitioned reading with exact mode and node_ids.

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

• lanhu_get_design_previewA
  4.7/5.0
  Behavior4/5

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

  Annotations already indicate read-only and open-world hints; description adds that preview is not authoritative for dimensions/colors, complementing annotations without 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?

  Two concise sentences, no filler, front-loaded with purpose and key limitation. Every sentence adds value.

  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 simple tool with 2 params and no output schema, description sufficiently covers purpose, limitations, and sibling relationships; no gaps.

  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 covers 100% of parameters with descriptions; description adds context beyond schema, e.g., that 'design' can be omitted if image_id in URL, enhancing 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 the tool retrieves a preview image to confirm visuals and text burning, distinguishing it from schema and slices tools.

  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 states when to use this tool (visual confirmation) and when not to (rely on schema/slices for authoritative geometry), providing clear guidance vs alternatives.

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