Server Quality Checklist

Tool Scores

• get_diagramA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool fetches data and returns a specific structure, implying a read-only operation. No side effects or additional behaviors are mentioned, which is acceptable for a fetch 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 with zero wasted words. The first sentence states the action and return value, the second provides essential usage guidance. Perfectly front-loaded and concise.

  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 simple tool with one parameter and no output schema, the description covers the return shape and the critical usage context (predecessor to edit_diagram). It lacks information about error scenarios or authentication, but these are often implicit or handled elsewhere.

  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 has 100% coverage—the only parameter 'diagramId' is described as 'The diagram to fetch.' The description does not add extra detail about the parameter's format or constraints, so the value added beyond the schema is minimal, meeting the baseline.

  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 specifies a concrete action ('Fetch') and a specific resource ('diagram's raw IR...'), clearly distinguishing it from sibling tools create_diagram and edit_diagram. It outlines exactly what is returned (nodes, groups, edges, version).

  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 advises calling this tool before edit_diagram to obtain valid IDs and the correct version. While it does not list alternatives or when not to use it, the usage context is clearly stated and actionable.

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

• create_diagramA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses that it is a create operation, returns a deterministic layout, and the canvas is anonymous. It does not mention auth or rate limits, but the behavioral traits are well-covered for a creation tool.

  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 lengthy but well-organized with clear sections, bullet lists, and an example. Every part adds value; however, it could be slightly more terse without losing clarity.

  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 no annotations and no output schema, the description covers input thoroughly and output sufficiently, including return fields and what to do with the URL. It references sibling tools but does not elaborate on their usage. Overall, it is complete for the tool's 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?

  The description adds extensive value beyond the input schema, including a full worked example, lists of valid kind.catalog and type values, edge kinds, and group types. It compensates for any gaps in schema descriptions, making the parameters fully understandable.

  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 creates a new architecture diagram from a user-authored graph and returns a shareable URL, SVG, and Mermaid. It distinguishes itself from sibling tools (edit_diagram, get_diagram) by focusing on creation, though not explicitly naming them.

  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 detailed guidance on what to include (semantics, not layout) and what not to send (x/y/position/pinned). It includes a worked example. However, it does not explicitly state when to use this tool over alternatives or when not to use it, though sibling context is available.

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

• edit_diagramA
  4.6/5.0
  Behavior4/5

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

  No annotations exist, so the description carries full burden. It discloses that ops are validated, applied, re-layout, re-render. It explains the version-based conflict error (STALE_VERSION) and side effects (remove_node also drops edges). It mentions automatic geometry computation. Lacks details on authentication, rate limits, or reversibility, but what is provided is substantial.

  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 well-structured: concise overview, critical prerequisite call, enumerated operation list with definitions, worked example, and return fields. Every sentence is informative and earns its place, with key usage warnings front-loaded.

  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?

  Given the tool's complexity (3 parameters, one being a large array of operations), the description is remarkably complete. It covers prerequisite calls, error handling, all operation semantics, a concrete example, and the return value structure. No output schema exists, but the return fields are listed explicitly.

  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 67%, but the description compensates thoroughly. It explains each operation type in detail, including behavioral effects (e.g., 'insert_between' splices an edge), constraints (e.g., 'Never send x/y/position'), and formatting guidance. This adds significant meaning beyond the bare schema structure.

  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 'Apply a list of operations to an EXISTING diagram', specifying the verb (apply), resource (existing diagram), and scope. It distinguishes itself from siblings (create_diagram for new, get_diagram for reads) implicitly through context.

  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 instructs 'ALWAYS call get_diagram(diagramId) first' and explains version-based conflict handling. It provides a worked example. However, it does not explicitly state when not to use this tool (e.g., for creating a new diagram instead of editing).

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