Server Quality Checklist

Tool Scores

• mdk-docsB
  3.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to repeat safety. The description adds the four operation types but does not disclose any additional behavioral traits such as rate limits, authentication requirements, or side effects (e.g., whether searches modify state). The description is consistent with annotations, adding minimal value beyond them.

  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 a single sentence that front-loads the main purpose. It is concise with no wasted words. However, it could be slightly more structured (e.g., listing operations) for easier scanning, but still effective.

  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 tool with six parameters and four modes, the description is minimal. It does not explain when to use each operation, return value expectations (no output schema), or how folderRootPath affects behavior. It is adequately complete given the rich schema, but additional context would improve selection and 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?

  Schema description coverage is 100%, meaning the tool tip in the schema already explains each parameter. The description adds no additional meaning beyond the schema; it only provides a high-level overview. Baseline score of 3 is appropriate since the schema carries the semantic burden.

  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 tool's purpose: 'Unified tool for accessing MDK documentation including search, component schemas, property details, and examples.' It uses specific verbs ('accessing') and resource ('MDK documentation'), and differentiates from sibling tools (mdk-create, mdk-gen, mdk-manage) by focus on documentation. No explicit sibling differentiation, but the naming and brief description suffice.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides no guidance on when to use this tool versus alternatives. It does not state prerequisites, exclusions, or context for selecting among the four operations. With siblings like mdk-create and mdk-manage, the agent receives no help choosing this tool over others.

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

• mdk-manageB
  3.4/5.0
  Behavior3/5

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

  Annotations provide destructiveHint=true (can destroy), idempotentHint=true (safe to retry), and openWorldHint=true (side effects). The description adds the list of operations but does not disclose specific behavioral traits like what gets destroyed or auth requirements. It does not contradict annotations, so it provides some additional context beyond annotations.

  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 a single sentence that effectively summarizes the tool's capabilities, front-loading the key purpose. It is concise, though it could be slightly improved by listing operations in a clearer format (e.g., bullet list).

  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 description covers the main operations but lacks context such as prerequisites (e.g., existing project), output details, or common use cases. Given the tool's complexity and absence of an output schema, the description is minimally adequate but leaves 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 coverage is 100% with descriptions for each parameter. The description adds a summary of operations in the tool-level text, but the enum descriptions in the schema already explain each operation. No new parameter-level meaning is added beyond the schema, so baseline score of 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 it handles multiple specific operations (build, deploy, validate, migrate, show QR code, mobile app editor), making its purpose unambiguous. It distinguishes from siblings like mdk-create (creation) and mdk-docs (documentation) by focusing on management actions.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description does not explicitly state when to use this tool versus its siblings (mdk-create, mdk-docs, mdk-gen). While the operations list implies management tasks, no direct differentiation or context for choosing this tool over alternatives is provided.

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

• mdk-genA
  3.5/5.0
  Behavior4/5

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

  Annotations provide readOnlyHint and idempotentHint, indicating no state mutation. Description adds clarity by explaining that generation returns prompts for LLM processing rather than writing files, which aligns with annotations and provides valuable behavioral context.

  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?

  Description is two sentences, front-loading the core action and output. No filler or redundancy; every sentence adds value.

  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 8 parameters and no output schema, the description is somewhat complete but lacks detail on return format (e.g., structure of prompts) and usage context relative to sibling tools. Schema covers parameter details, but the description could provide more guidance on when to choose each artifactType in practice.

  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%, so parameters are well-documented. Description adds context about artifact types and their output (prompts vs search), but does not significantly enhance understanding of other parameters like folderRootPath or pageType beyond what schema already provides.

  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?

  Description clearly states it generates MDK artifacts (pages, actions, i18n, rule) and returns prompts or search results. It specifies the resource and action, but does not explicitly differentiate from sibling tools like mdk-create or mdk-manage.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No explicit guidance on when to use this tool versus alternatives like mdk-create, mdk-docs, or mdk-manage. The description implies usage for generation but lacks when-not or context for choosing among siblings.

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

• mdk-createA
  4/5.0
  Behavior3/5

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

  Annotations already provide destructiveHint: true and idempotentHint: true. The description restates the creation action but adds no new behavioral details beyond the schema. It does not contradict 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, concise and front-loaded. Every sentence adds value, with no unnecessary words.

  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 5 parameters and no output schema, the description adequately covers purpose, scope, and templates. It could mention return values or error conditions, but overall provides sufficient context for use.

  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%. The description mentions templates and scope, which are already covered in the schema descriptions. It adds high-level context but no additional meaning beyond the structured 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 tool creates MDK projects or entity metadata using templates, and distinguishes from sibling tools (mdk-docs, mdk-gen, mdk-manage) by focusing on creation. The verb 'Creates' and resource specification are specific and unambiguous.

  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: for initializing new projects or adding entity metadata to existing projects. It does not explicitly state when not to use or provide alternatives, but the guidance is clear for the intended use case.

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