Server Quality Checklist

Tool Scores

• generate_umlA
  3.8/5.0
  Behavior3/5

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

  Annotations already provide idempotent and non-destructive hints, so the bar for transparency is lower. The description adds the range of supported diagram types but does not disclose potential file output behavior (e.g., output_dir) or the meaning of the code parameter.

  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, front-loaded sentence with no filler. Every word contributes to stating the action, scope, and examples.

  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 6 parameters and no parameter descriptions, the description is too terse to fully guide invocation. It explains what the tool does but not how to construct the required code input or what optional parameters control, though an output schema exists to mitigate return-value ambiguity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate for parameter meaning. It only gives examples for diagram_type but leaves code, scale, theme, output_dir, and output_format unexplained, relying on property names alone.

  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 verb 'Generate' and the resource 'any UML or diagram by type', with explicit examples (class, sequence, mermaid, d2). This distinguishes it from sibling tools like validate_uml, list_diagram_types, and generate_uml_batch.

  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 implies this is the primary single-generation tool, and sibling names suggest validation and batch alternatives. However, it does not explicitly state when not to use it or give direct comparisons to generate_uml_batch.

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

• validate_umlA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate read-only, non-destructive, and idempotent behavior. The description adds meaningful behavioral context: it explicitly lists what is validated (type, format, code length, syntax) and that it returns 'errors and suggestions'. This goes beyond the annotations and clearly discloses the local nature (no remote call), without contradicting any 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 model of conciseness: two sentences front-load the core purpose and context, followed by a clear statement of the return behavior. Every word contributes; there is no filler or redundancy.

  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 straightforward local validator, the description, combined with annotations and the presence of an output schema, is sufficiently complete. The tool's role is clearly delineated relative to siblings, and the description covers the essential behavior. Minor gaps about parameter behavior reduce it from a perfect score.

  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 0%, so the description must compensate. It provides partial semantics by referencing 'diagram type' (diagram_type) and 'code length' (code), but omits any explanation for `strict` and `output_format`. The description does not fully substitute for the absence of schema 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 states a specific action (validate) on a specific resource (UML diagram code) and enumerates what is validated: diagram type, format, code length, and basic syntax. It distinguishes itself from sibling generation tools by adding 'before render (no Kroki call)', clearly positioning this as a pre-render validation step.

  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 phrase 'before render (no Kroki call)' clearly indicates when to use this tool as a local pre-flight check, contrasting with the generation tools. However, it does not explicitly name alternatives or state when NOT to use it, leaving some implicit nuance.

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

• generate_uml_batchA
  4.5/5.0
  Behavior4/5

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

  Annotations already cover idempotent and non-destructive behavior. The description adds useful context about the return format ('list of per-index results or errors') and the optional shared output_dir. This goes beyond the annotations without contradicting them.

  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, front-loaded with purpose, and includes the necessary parameter and return details without any waste. 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?

  The description covers batch behavior, item structure, return type, and shared directory. There is an output schema for detailed return values, so the description need not repeat that. It could mention edge cases like empty items, but overall it's complete for a tool of this complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0%, but the description compensates by outlining the item structure with fields and optionality (diagram_type, code, output_format?, theme?, scale?) and explaining that output_dir is shared for all items. This gives the agent a clear understanding of the parameters beyond bare 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 'Generate multiple diagrams in one call', using a specific verb and resource that distinguishes it from the sibling tool generate_uml (single). It also mentions 'Each item is like generate_uml', reinforcing its role as the batch counterpart.

  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 implies batch usage by framing it as 'multiple diagrams in one call' and referencing generate_uml's parameter structure. It doesn't explicitly say when to choose this over repeated calls but conveys the benefit. No explicit exclusions, but sufficient guidance for typical use.

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

• list_diagram_typesA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds value by explaining the tool returns the same data as the 'uml://types resource' and enumerates the data fields (backend, description, formats), providing useful contextual insight 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 concise and front-loaded: it states the action and resource in the first sentence, then gives a brief usage hint in the second. Every word earns its place, with 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?

  For a parameterless list tool with a rich output schema and thorough annotations, the description covers purpose, data source equivalence, and when to use it. It is sufficiently complete for an agent to decide when to invoke it and what to expect.

  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 takes no parameters, so the baseline is 4. The description makes it clear there is nothing to configure, and the empty input schema confirms this. No additional parameter explanation is needed.

  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 ('List') and the specific resource ('supported diagram types'), adding detail on the data fields ('Kroki backend, description, and formats'). It distinguishes from sibling tools that validate or generate diagrams, 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 Guidelines4/5

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

  The description provides an explicit usage condition: 'Use when the client cannot read resources.' This gives clear context for when the tool is appropriate, though it does not explicitly mention alternatives or exclusions relative to sibling tools. The condition effectively implies that the uml://types resource is the preferred equivalent.

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