Server Quality Checklist

Tool Scores

• listA
  3.8/5.0
  Behavior3/5

  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 clearly indicates a read-only listing behavior and explains the drill-down mechanism, but it does not mention the return format, what happens if an invalid path is passed, or any side-effect guarantees. 'List' implies no mutation, but more detail on output or error behavior would strengthen 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?

  Two sentences carry the entire definition with zero filler. The main purpose is front-loaded, and the optional-argument behavior is explained efficiently with concrete examples.

  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 one optional parameter and no output schema, the description covers the core use cases: top-level listing and category drill-down. It gives examples and the dot-separated path convention. The only notable gap is specifying the output shape or behavior for an invalid category path, but that's minor for a simple read-only list 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?

  The input schema already fully documents the category parameter: dot-separated path, examples, and 'omit or leave empty' behavior. The description largely restates this same information and only adds the context of 'subcategories and skills', so it adds minimal value beyond the schema. Baseline 3 applies given 100% schema coverage.

  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 states a specific verb ('List') and a clear resource ('top-level categories', 'subcategories and skills'), and explains the optional drill-down behavior. It doesn't explicitly name sibling tools to distinguish itself, but 'Use this to explore the skill library structure' provides enough context to separate it from search/read/keywords/help.

  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 a clear usage cue ('Use this to explore the skill library structure') and explicit invocation patterns: call without arguments for top-level categories, or pass a dot-separated path to drill in. It stops short of a 5 because it doesn't explicitly say when to use a sibling tool like search instead.

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

• keywordsA
  4.2/5.0
  Behavior4/5

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

  No annotations exist, so the description carries the full burden — and it delivers: it discloses the return value (full keywords array), the source resolution (SKILL.md vs. skill file), and the two accepted path shapes. It doesn't cover error/empty-path behavior, but for a simple read-only lookup that is a minor gap rather than a serious one.

  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 sentences with zero filler: the verb+resource statement is front-loaded, the second sentence explains resolution behavior, and the third gives the practical use case. 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 single-parameter lookup with no output schema, the description covers the return value, the two input path semantics, and the intended use case. The only real omission is the shape of the returned array, but the description's 'full keywords array' phrasing plus a low-complexity surface makes this adequately 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 coverage is 100% — the schema already documents the dot-separated format with concrete examples and the no-.md-extension rule. The description reinforces the same examples but adds no meaning beyond the schema, so the baseline 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?

  Starts with a specific verb+resource pair ('Retrieve the full keywords array for a specific category or skill') and immediately clarifies the two path types. The closing phrase 'without reading the full content' explicitly differentiates it from the sibling `read` tool, so an agent can tell them apart without opening any schemas.

  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: use this to understand what terms a skill covers without loading full content, and it explains how category vs. skill paths resolve. It does not explicitly name alternatives or state when NOT to use it, but the contrast with `read` is implied strongly enough for a 1-parameter lookup tool.

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

• readA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full behavioral burden. It discloses that frontmatter metadata is stripped, that category paths return SKILL.md body plus children, and that skill paths return Markdown body. It does not cover error behavior or explicitly confirm non-mutating behavior, but the read action and output details make the tool's behavior reasonably 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?

  The description is compact and front-loaded with the core purpose, followed by path-type behavior and the important help-first warning. Every sentence contributes useful information with no repetition or 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?

  Despite having no output schema, the description explains the return behavior for both category and skill paths and notes frontmatter stripping. Minor gaps such as invalid-path behavior and the exact shape of the children list keep it from being fully complete, but it is sufficient for a simple single-parameter read 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?

  The schema already provides 100% coverage for the single path parameter, including dot-separated path examples and the instruction not to include the .md extension. The description reinforces the path-type distinction but does not add substantial parameter semantics beyond what the schema already documents, so the baseline 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 the action and resource: 'Read the full content of a specific skill or category.' It also distinguishes behavior for category paths versus skill paths, making the tool's purpose unambiguous and separable from sibling tools like list, search, and keywords.

  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 for how to use the tool based on path type, and it includes an explicit usage prerequisite: 'Always call help first if unsure how to use the library.' It does not explicitly name alternatives or say when not to use this tool, but the guidance is still strong.

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

• helpA
  4.6/5.0
  Behavior4/5

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

  With no annotations supplied, the description carries the full behavioral burden and does disclose the progressive step behavior and the full-overview fallback. It could explicitly state that this is a read-only informational tool, but the described act of returning documents makes side effects highly unlikely.

  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?

  Every sentence earns its place and the core purpose is front-loaded. The long list of frontend-related task types in the IMPORTANT sentence is somewhat dense, but it is necessary to define the mandatory scope of the tool.

  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 one optional parameter, no annotations, and no output schema, the description covers purpose, mandatory usage context, parameter semantics, and return behavior completely. An agent has everything needed to correctly invoke this tool on the first call.

  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 documents the step parameter with 100% coverage, so the baseline is 3. The description adds usage guidance beyond the schema by prescribing step=1 as the required first call and framing steps 2-5 as subsequent stages in a progressive guide. This is meaningful added 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 uses a specific verb-resource pair ('Get usage instructions and recommended workflow') and further establishes it as the mandatory entry point for interface/frontend work. This clearly distinguishes it from sibling tools like list, search, read, and keywords, which obviously handle different resources.

  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 states when this tool MUST be used (any task involving interface development, UI/UX, animation, visual styling, etc.) and prescribes a concrete workflow: always start with step=1, then proceed through steps 2-5. It also documents the behavior when step is omitted, leaving no doubt about how to invoke it.

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

• searchA
  4.6/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden, and it delivers: it discloses exact case-insensitive matching, OR logic across keywords, and scope behavior across SKILL.md files and subcategories. These are non-obvious behavioral details that an agent needs to predict results correctly.

  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 front-loaded with the core purpose, then moves efficiently through matching behavior and scoping rules. Every sentence adds distinct information, and there is no filler or redundant restating of the tool name.

  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 two-parameter search tool, the description covers selection and invocation well, including matching semantics and category scoping. It would be slightly stronger if it specified the return format more concretely, but 'Any keyword match returns the item' gives a reasonable expectation in the absence of an output schema.

  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 already 100%, so the baseline is 3. The description adds value by explaining how keyword matching behaves ('any keyword match returns the item') and how the category parameter changes search scope. This meaningfully supplements the schema without repeating it.

  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: 'Search for categories or skills by keywords.' It goes beyond a generic statement by detailing exact matching, case-insensitivity, OR logic, and global vs. category-scoped behavior, which makes its purpose easy to distinguish from sibling tools like list, read, and help.

  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 when to include or omit the category parameter: 'Without a category, searches globally... With a category, searches within that category's skills and subcategories.' It does not explicitly name alternatives or say when not to use this tool, but the scoping guidance is direct and actionable.

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