Server Quality Checklist

Tool Scores

• view_planA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses important behavior: refs are pointers, not content, and the server opens the file itself. It also states the return format (a single URL line). It does not explicitly claim read-only status, but the purpose implies no modifications.

  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 well-structured paragraph that front-loads the purpose, then provides timing, content limits, and return behavior. Every sentence adds value with 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?

  Despite complex nested schema for diagram and refs, the description covers essential use, constraints, and return value, especially since there is no output schema. It lacks explicit error handling or exclusions but is sufficient for an agent to invoke the tool 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 coverage is 100%, so the baseline is 3. The description adds a crucial clarification that refs are pointers and the server opens the file itself, which goes beyond the schema's descriptions and helps correct usage.

  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 identifies the tool as showing a plan on a local web page, using a specific verb and resource. It does not explicitly distinguish from sibling tools like view_report or view_diagram, but the focus on 'plan' makes the purpose evident.

  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?

  Explicitly instructs to call the tool BEFORE making changes, once an approach is decided. It does not mention when not to use it or alternatives, but the timing advice is precise and actionable.

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

• view_reportA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and discloses key behaviors: the page automatically shows every changed file with per-line diffs, and the return contract is 'Returns a single line with the page URL - reply with that line only.' This is valuable beyond the schema, though it omits error cases or prerequisites.

  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 dense paragraph with no filler. It follows a logical flow: purpose, when to call, what to include, expected output, and every sentence contributes to the agent's understanding.

  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 purpose, timing, parameter guidance, and output format, which is solid given no output schema. It could better address how this relates to sibling tools like view_plan and view_diagram, but it is adequate for a 5-parameter tool.

  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 baseline 3 applies. The description adds usage hints like summary max 3 sentences and refs using anchors, but these mostly echo the schema descriptions rather than introduce new parameter 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 clearly states it shows what you did on a local web page instead of chat, using a specific verb and resource. It also distinguishes itself by noting the page includes per-line diffs, which is a unique capability versus chat output.

  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?

  It explicitly says 'Call this AFTER you have finished the work,' giving a clear timing guideline. It also instructs not to describe edits in chat but to point at the page, but it does not directly contrast with sibling tools like view_plan or view_diagram.

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

• view_diagramA
  4.9/5.0
  Behavior5/5

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

  The description discloses critical behavioral traits beyond the schema: the hard limit of 9 nodes, the instruction to never send colors/coordinates/SVG (server handles layout/styling), and the return format ('a single line with the page URL - reply with that line only'). These are not present in the annotations (none provided) and are essential for correct usage.

  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 compact yet dense with actionable information. Every sentence earns its place: purpose, use case, limit, request formatting, and response handling. It avoids filler and front-loads the most critical information within the first two sentences.

  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 nested object schema and the absence of output schema/annotations, the description is remarkably complete. It explains the return value ('single line with the page URL'), usage context, and constraints (node limit, no styling). The sibling tools are 'view_plan' and 'view_report', and the description clearly delineates this tool's niche, leaving no major gaps for the agent.

  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 schema already has 100% coverage in parameter descriptions, so the baseline is 3. The description adds value by summarizing the key constraint ('Hard limit of 9 nodes') and the anti-pattern for visual properties, which is not fully covered in the schema properties but is mentioned in the nested diagram description. It doesn't repeat every field, but reinforces the most load-bearing semantic rules.

  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: 'Draw a diagram on a local web page' immediately states the action and output medium. It further clarifies the tool's scope by explicitly saying 'without a plan or a report attached', which distinguishes it from sibling tools (view_plan, view_report). The purpose is unmistakable.

  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 explicitly tells when to use this tool ('when the user asks how something works and the answer is a picture'), and provides clear exclusion criteria ('without a plan or a report attached'). It also names the alternatives implicitly by contrasting with plans/reports, and gives explicit guidance for splitting complex subjects into multiple calls.

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