Server Quality Checklist

Tool Scores

• generateDataDiagramA
  3.5/5.0
  Behavior2/5

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

  With no annotations, the description carries full behavioral transparency burden. It only states the tool converts data to a diagram format, without disclosing limitations, output details, or side effects. This is minimal disclosure for a file-processing tool.

  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 deliver purpose and usage guidance efficiently, with no wasted words. Front-loaded with the core action.

  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 the tool has no output schema and three parameters, the description covers basic purpose and usage. However, it lacks details on diagram output type, error handling, or size constraints, which are relevant for raw data input.

  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 the schema already documents all parameters. The description adds no parameter-level details, but the context (e.g., 'structured data') reinforces usage. Baseline 3 is appropriate.

  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 generates diagrams from structured data (JSON, YAML, CSV, XML). However, it does not explicitly differentiate from sibling tools like generateCodeDiagram or generateSystemDiagram, missing a chance to achieve a top score.

  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 explicit usage context: 'visualizing raw data structures, configuration files, or API responses.' It does not mention when not to use or name alternative tools, but the context is sufficient for most scenarios.

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

• generateImageDiagramA
  3.9/5.0
  Behavior3/5

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

  Discloses analysis process (identify components, relationships, hierarchy) but no details on limitations, accuracy, or side effects. No annotations provided, so description carries moderate burden.

  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 well-structured sentences with no extraneous content. First sentence defines purpose and examples, second explains mechanism. Every clause earns its place.

  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?

  No output schema, so description should clarify output format. 'ToDiagram custom format' is vague. Missing constraints like file size or supported image complexity. Adequate but not comprehensive.

  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 baseline of 3. Description adds minimal value beyond schema: it mentions analysis but doesn't elaborate on parameter roles beyond what's in the schema.

  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 'Convert an image into a ToDiagram custom format diagram' with examples of image types (screenshot, diagram, sketch, architecture). Distinguishes from sibling tools like generateCodeDiagram and generateMermaidDiagram by specifying the input source is an image.

  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?

  Implies use when you have an image and want a diagram, but lacks explicit when-not-to-use or alternatives. Sibling tools are listed but not compared directly.

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

• generateSystemDiagramA
  4/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It describes the output style (icons, nesting) but does not disclose behavioral traits like read-only nature, performance, or error conditions. Adequate but not detailed.

  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?

  Four sentences, each valuable: purpose, style guidance, nesting advice, use cases. No redundant or unnecessary content.

  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?

  Covers the main aspects of diagram generation with nodes/edges, icons, and nesting. Could mention direction parameter impact, but schema covers it. Sufficient for the complexity.

  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 baseline is 3. Description adds context about icon format and nesting advice but does not significantly extend beyond the schema's property 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 it generates 'High-level system/architecture diagrams with grouped image/icon nodes' and lists specific use cases (repositories, platform overviews, services, environment maps). This distinguishes it from siblings like generateCodeDiagram or generateMermaidDiagram.

  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?

  Provides guidance on when to use (listed use cases) and how to structure (nested nodes, minimal fields). Lacks explicit when-not-to-use or comparison to alternatives, but context is clear enough.

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

• generateMermaidDiagramA
  4.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must disclose behavioral traits. It mentions support for Iconify icons and flowchart-only constraint, but does not explicitly state the output format (raw Mermaid code). The title and description imply text-only output, but this is not confirmed.

  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 concise with three sentences, each serving a distinct purpose: usage condition, alternatives, and parameter details. Front-loads the key instruction, no fluff.

  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 tool's simplicity (2 params, no output schema), the description covers purpose, usage, and parameter semantics adequately. However, it lacks explicit mention of the return data (raw Mermaid syntax), which would enhance completeness.

  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%, so baseline is 3. The description adds value by explaining the Iconify icon syntax and the flowchart-only constraint for the 'content' parameter, enhancing understanding beyond the schema.

  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 purpose: generating raw Mermaid syntax for flowcharts when explicitly requested. It distinguishes from sibling tools by specifying when to prefer alternatives, making the purpose unambiguous.

  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 only when a user explicitly requests raw Mermaid syntax' and provides clear alternatives for other cases (e.g., generateSystemDiagram for architecture). Also notes that only flowcharts are supported.

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

• generateCodeDiagramA
  4.6/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It discloses important behaviors: imageUrl hides rows, iconUrl preserves rows, parent nodes should omit imageUrl. This covers rendering trade-offs. However, it doesn't mention error handling or return structure, but for a diagram tool, these are secondary. The behavioral context added is valuable and not in schema.

  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, each contributing unique information: purpose, usage distinction, and behavioral note. No filler. Front-loaded with main purpose, resulting in high information density.

  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 tool has nested objects and 2 top-level parameters with 100% schema coverage. No output schema. Description covers key behavioral differentiators (image vs icon, parent nodes) and usage context. It doesn't explain return format, but that's acceptable given schema coverage. Overall, adequate for 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?

  Schema description coverage is 100%, so baseline is 3. The description adds beyond schema: explaining the distinction between imageUrl and iconUrl, guidance for parent nodes, and direction defaults. This enriches parameter understanding without repeating schema 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 'Code-level or detailed component diagrams with key-value rows plus optional icons/images', which specifies the verb (generate) and resource (code diagram) and distinguishes it from generateSystemDiagram. It explicitly says 'For high-level system visuals with mostly image nodes, use generateSystemDiagram', providing clear sibling differentiation.

  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: 'Code-level or detailed component diagrams' and when-not: 'For high-level system visuals with mostly image nodes, use generateSystemDiagram'. It also gives a behavioral note about imageUrl vs iconUrl, which helps the agent decide based on needs.

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