Server Quality Checklist

Tool Scores

• generate_diagramC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden of behavioral disclosure. It reveals that it writes a file to images/ or --outDir, which is useful, but doesn't disclose whether it overwrites existing files, what format the file name takes, or failure modes. For a mutation (file-writing) tool with zero annotation coverage, this is thin.

  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?

  A single efficient sentence that communicates core purpose and output location. No wasted words, but the CLI-flag phrasing ('or --outDir') is slightly informal for a tool description.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a file-writing tool with no annotations and no output schema, the description should explain more: overwrite behavior, file naming, the meaning of the id choices, and relationship to generate_all_fork_diagrams. The enum of 6 valid ids is documented only in the schema, leaving the agent without guidance on what each diagram represents.

  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 50% (outDir is documented in schema, id is not). The description adds the default output directory ('<repo>/images') and the CLI-style '--outDir' flag mention, which adds some value. However, it doesn't explain the id enum values or their semantics beyond existence in the schema.

  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 uses a specific verb+resource ('Generate one Disler-style diagram and write it') against sibling generate_all_fork_diagrams, implying single vs batch output. However, it doesn't explicitly distinguish itself from the sibling generate tool or clarify what 'Disler-style' means concretely.

  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 guidance on when to use this tool vs generate_all_fork_diagrams. Sibling named 'generate_all_fork_diagrams' implies this is the single-diagram version, but the description never states this tradeoff or any exclusions.

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

• generate_all_fork_diagramsB
  3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. The description discloses that it writes files (svg-07 through svg-12) to a directory, which is some behavioral transparency, but doesn't state whether existing files are overwritten, whether the command is idempotent, what naming constraints exist, or what happens on failure. For a file-writing tool with zero annotations, this is insufficient context.

  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 brief and front-loaded, naming the outputs first ('svg-07 through svg-12'), then the destination. No wasted words. The single sentence covers purpose and parameter. Efficient formatting.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  This is a batch file-generation tool with no output schema and no annotations. It has one optional parameter. The description explains which files are written and where, but doesn't state whether this is a destructive write, whether files already exist, whether it regenerates from a canonical source, or what relationship svg-07 through svg-12 have to each other. For a tool that writes six files to disk, more behavioral context is warranted.

  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% for the single parameter outDir, which is documented as 'Absolute output directory. Defaults to <repo>/images'. The description adds the clarification that this overrides the default output location. With a single param and high coverage, the description complements the schema reasonably well by linking outDir to the filesystem behavior.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose3/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description says 'Generate svg-07 through svg-12 into images/ (or outDir)' with verb 'Generate' and specific resource (svg-07 through svg-12). It distinguishes from siblings like generate_diagram by targeting a specific batch, but the exact nature of 'fork diagrams' vs plain 'diagrams' is unclear from title alone.

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

  Usage Guidelines3/5

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

  The description implies usage (generating a specific batch of files into an output directory), and mentions outDir as an option. However, it does not explicitly state when to use this versus generate_diagram, nor when-guidance or exclusions. It's implied that this is for batch-generating fork diagrams specifically.

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

• preview_diagramA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses that output is SVG markup and that nothing is written to disk, which addresses the primary behavioral question (side effects). However, it doesn't disclose other traits such as whether the in-memory diagram is stored/queryable, any auth/permission needs, or performance/rate-limit considerations. The disclosure is minimal but does cover the most important behavioral aspect.

  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?

  One compact sentence with zero waste. It front-loads the primary purpose (generate diagram), includes the output format (SVG markup), and adds the key side-effect clarification (no disk write). Ideal conciseness for a tool with a single well-documented parameter.

  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 single-parameter tool with 100% schema coverage and no output schema, the description is mostly complete. It clarifies output format and side-effect absence. However, with no annotations and the presence of closely-related siblings (generate_diagram, generate_all_fork_diagrams), a bit more context distinguishing this preview mode from full generation would round it out.

  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% with a single parameter fully enumerated via enum (six concrete diagram ids). The description adds context that the parameter selects which pre-defined diagram to generate. Since the single parameter is fully documented in the schema with a clear enum, the description needs to add little—and it adequately frames the parameter's role in the generation flow.

  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 verb (generate), resource (diagram), and key trait (returns SVG markup, in-memory). The 'does not write to disk' qualifier adds useful scope. It's slightly weaker on distinguishing from siblings like generate_diagram (which presumably does write to disk), but the in-memory note helps differentiate.

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

  Usage Guidelines3/5

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

  The description implies this is for in-memory preview work ('does not write to disk'), suggesting a use case distinct from generation that persists. However, it doesn't explicitly name alternatives like generate_diagram or state when to prefer one over the other. The 'preview' purpose is clear context but no exclusions or alternatives are named.

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

• list_diagramsA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It's clearly a read-only listing operation ('list... with reference originals and descriptions'), which is implicitly non-destructive. However, it doesn't disclose return format, pagination, or ordering behavior. For a simple list tool with no annotations, this is adequate but not rich.

  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?

  Single sentence, zero waste. Every element earns its place: the verb, the resource, the ID range, and the output content. This is an example of efficient minimal specification.

  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 parameterless list tool, the description is quite complete. It conveys what will be listed (ids, reference originals, descriptions) and the scope (svg-07..svg-12). There's no output schema to supplement, so the description itself carries the return-value expectation, which it does reasonably well. Could optionally name sibling tools like generate_all_fork_diagrams as next steps, but that's a minor 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 tool has 0 parameters, so there are no parameter semantics to explain. The baseline of 4 for 0-parameter tools applies. The description's mention of 'reference originals and descriptions' hints at the expected output content, which adds useful context beyond the empty schema.

  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 the tool 'List diagram ids' with a specific resource (fork README diagrams) and the specific IDs range (svg-07..svg-12). It distinguishes from sibling tools like generate_diagram and preview_diagram by clarifying this is a listing function, not a generation or preview tool. Clear verb+resource+scope.

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

  Usage Guidelines3/5

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

  The description implies this is a discovery/preview tool ('list diagram ids the generator can produce'), which suggests using it before generating. However, it doesn't explicitly name alternatives or state when-not-to-use. Sibling tools like generate_all_fork_diagrams imply this is a precursor, but the description doesn't make that relationship explicit.

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

• list_style_tokensA
  4.2/5.0
  Behavior4/5

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

  With no annotations at all, the description carries the full burden of behavioral disclosure. The description clearly signals a read/passive operation ('Return', 'extracted from') and specifies the content domains returned (color palette, glyphs, font stack, structural rules). It doesn't describe output shape or whether extraction happens lazily, but for a zero-parameter retrieval tool, the intent and side-effect profile are 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 a single, focused sentence with zero wasted words. It front-loads the return value and enumerates the specific categories of style data. It is appropriately sized for a zero-parameter retrieval tool.

  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 zero-parameter, read-only style-token retrieval tool with no output schema required, the description covers essential information: what data is returned and its source (the original Disler fusion-harness SVGs). It doesn't detail the exact structure/nesting of the returned tokens, but given the tool has no params and no output schema, this level of detail is arguably adequate for an agent to invoke and consume the result.

  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 0 parameters, and the schema coverage is 100% (vacuously, since there's nothing to describe). With no parameters, the baseline score is 4, and the description clearly enumerates what data will be returned, which is the relevant semantic information an agent needs even without 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 uses specific verbs and resources: 'Return the color palette, glyphs, font stack, and structural rules extracted from... SVGs.' This clearly distinguishes it from sibling tools like list_diagrams (which presumably lists diagrams) and generate_diagram (which generates diagrams). The resource (Disler style tokens) and action (return/extract) are unambiguous.

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

  Usage Guidelines3/5

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

  The description implies this is a read-only retrieval tool for style information, which is reasonably distinct from siblings (listing/generating diagrams). However, it doesn't explicitly state when to use this vs alternatives, nor does it explain what the downstream use is (e.g., 'use these tokens when generating diagrams'). The purpose is clear enough that an agent could infer usage, but there's no explicit context or exclusion guidance.

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