Server Quality Checklist

Tool Scores

• create_diagramB
  3.4/5.0
  Behavior2/5

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

  The annotations are empty/uninformative (all false hints), so the description carries the full burden of behavioral disclosure. It clearly indicates mutation by saying 'create', but it does not disclose what happens if output_path already exists (overwrite defaults to false), how the file lives in layout impacts x/y coordinates, or what a successful invocation returns. No contradiction with annotations, but meaningful behavioral context is missing.

  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 sentence with zero filler: it states the output format, the source ingredients, and the key layout behavior. Each phrase earns its place, and the constructing verb is placed front and center.

  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?

  With 8 paramters, 2 required arrays, nested objects, no output schema, and a sibling set, this one-sentence description is not enough for an agent to correctly plan an invocation. It does not explain when to prefer this over update_diagram, what automatic layout means for x/y inputs, whether node IDs are used to correlate edges and groups, or what a successful call returns.

  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 does translate the main arrays into the tool's domain ('structured groups, nodes, and edges') and hints that layout is handled automatically, which is useful. However, it provides no semantics for overwrite, page_name, title, output_path, the 'kind' field on nodes, or how its edges/groups reference node IDs—leaving much of the schema unexplained.

  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 verb ('Create') and a concrete resource ('editable .drawio XML diagram'), and it details the construction inputs ('structured groups, nodes, and edges') plus the 'automatic layout' behavior. It naturally distinguishes itself from the sibling tools: server_info/inspect/validate act on existing diagrams, and update modifies, while this one creates a brand-new diagram.

  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 phrase 'Create a new' implies that this tool is for new diagrams rather than modifying an existing one, which gives some conditional guidance. However, the description does not explicitly mention siblings or say 'use update_diagram if the diagram already exists', so the usage distinction is left implied rather than stated.

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

• validate_diagramA
  3.6/5.0
  Behavior3/5

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

  Annotations cover read-only, idempotent, and non-destructive behavior, so the description need not repeat those. The description adds the specific validation checks performed, but it does not disclose the output format, return value, or outcome when invalid structures are detected, which would materially help an agent interpret the invocations.

  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?

  A single, front-loaded sentence that efficiently conveys the tool's purpose and the full list of validation checks. Every word carries information and there is no fluff or redundancy.

  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 one-parameter, read-only validation tool, the stated purpose and checks are clear, and the annotations cover safety behaviors. However, there is no output schema and no description of the return value or error/reporting behavior, so the agent cannot fully predict the result of a validation run. The description alone is not complete enough.

  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?

  The schema provides only an unannotated string property named input_path, and schema description coverage is 0%. The description never explicitly defines input_path as a path to a draw.io XML file, leaving the agent to infer this from the tool name and description. At 0% coverage, the description should compensate but does not add any parameter-specific meaning.

  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 clear, specific verb 'Check' and names a precise resource, 'draw.io XML structure', then explicitly lists the defect classes it detects: duplicate ids, invalid geometry, page bounds, dangling edges, and node overlaps. This makes its purpose distinct from siblings like create_diagram, update_diagram, and inspect_diagram.

  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 should be used to validate a draw.io diagram's correctness, but it does not explicitly state when to use the tool versus alternatives such as inspect_diagram. It mentions no exclusions or conditional context, so an agent must infer the appropriate usage from the tool's purpose and sibling names.

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

• update_diagramA
  3.7/5.0
  Behavior4/5

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

  Annotations only indicate that the operation is not read-only and not idempotent; the description adds meaningful behavioral context by stating it writes a separate output unless overwrite is explicitly enabled. This alerts the agent to the default non-destructive side-effect behavior, which is valuable beyond 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?

  Two dense sentences convey the operation scope and the overwrite behavior with no filler. The most decision-relevant fact—that output is separate unless overwritten—is stated and placed at the end without bloating the definition.

  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 mutation tool with no output schema and sparse parameter documentation, the description is adequate but not comprehensive. It provides the key operation summary and overwrite caveat, but does not help an agent construct valid operations or understand how output_path/overwrite interact in edge cases, leaving gaps compensated only by the raw schema.

  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 should carry parameter semantics, but it only mentions add nodes/edges/update-node operations at a high level. It does not explain input_path, output_path, overwrite semantics, or operation object requirements, leaving significant inference to the agent despite a fairly nested 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?

  Description clearly states the action: add nodes/edges or update a node in an existing draw.io file. It names the resource ('existing draw.io file') and distinguishes it from creating a new diagram, though it does not explicitly differentiate from inspect_diagram or validate_diagram.

  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 'existing draw.io file' conveys that this tool is for modifications rather than creation, and the separate-output note helps agents avoid unintended file overwrites. No explicit when-not-to-use or alternative routing is provided, but the context is clear enough for most selection decisions.

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

• inspect_diagramA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare the tool is read-only, idempotent, and non-destructive. The description adds meaningful behavioral context on top: it reads only the first page of a multi-page file and returns a specific subset of diagram information. 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 entire description is a single well-structured sentence that front-loads the action and scope and includes no filler. Every word in the sentence contributes to what the tool does and what it returns.

  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 simple one-parameter read-only tool, the annotations plus description give a good high-level picture: read first page, return diagram elements, safe to call. However, the complete lack of input_path documentation and the absence of explicit alternative routing leaves enough of a gap that the description is merely adequate rather than fully complete.

  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 by explaining input_path. It never explicitly states what input_path should contain, what path formats are supported, or that it must refer to an existing draw.io XML file. The parameter name is self-descriptive to a degree, but no real semantic guidance is provided.

  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 ('Read'), a resource ('first page of a draw.io XML file'), and concrete outputs ('nodes, edges, labels, and geometry'). This clearly distinguishes inspect_diagram from the create/update/validate siblings, which all perform different operations.

  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 read semantics strongly imply that this tool is for inspecting an existing draw.io file rather than creating or modifying one. However, it never explicitly says when to choose it over validate_diagram or server_info, nor does it give set exclusions.

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

• server_infoA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare this as read-only and non-destructive. The description adds semantic context about what information is exposed (allowed roots, supported workflows), going slightly beyond the annotations. It doesn't mention response format, but for a zero-parameter info endpoint this is not a critical gap.

  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 compact sentence with no filler or redundant restatement. It front-loads the actionable verb and object, making it easy to parse.

  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 trivial 0-parameter read-only server-info tool, the description is sufficiently complete. It states what the tool returns in broad terms. A more precise list of the exact response fields would help, but the current description is enough for correct invocation and outcome interpretation.

  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?

  There are no parameters, and the schema confirms this (100% coverage). The description does not need to elaborate on parameters because none exist.

  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 ('Show') and resource ('allowed roots and supported workflow information') with clear scope. It distinguishes itself from diagram-operation siblings (create_diagram, inspect_diagram, validate_diagram, update_diagram) as a general server introspection tool.

  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?

  While there is no explicit 'use when...' guidance, the description makes it evident that this tool is for retrieving server-level information, not performing diagram operations. The sibling list reinforces that boundary. No exclusions are needed because the tool's purpose is self-contextualizing.

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