Server Quality Checklist

Tool Scores

• preview_documentA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns base64 and distinguishes between full-fidelity PDF and PNG thumbnails. However, it does not mention side effects, permissions, error conditions, or behavior for unsupported file types, leaving gaps for an agent.

  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 no filler. The first sentence immediately states the action (produce a preview) and key options. Every word serves a purpose. Front-loaded with the verb and resource.

  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 output schema, the description includes the return type (base64) and its purpose (powers preview). For a simple transformation tool, this is adequate. Minor gaps: no mention of error behavior or size constraints, but overall complete for its complexity.

  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% with parameter descriptions. The description adds value by explaining 'full-fidelity PDF' and 'single-page PNG thumbnail', and by contextualizing that the preview powers a board viewer. This goes beyond the schema's dry descriptions.

  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 title and description clearly state the tool produces a preview (PDF or PNG) for the in-browser viewer. It specifies the two kinds and their defaults. However, it does not explicitly differentiate from sibling tools like render_document, though the focus on preview vs rendering is implicit.

  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 usage for generating previews in a board viewer ('Powers the board's document preview'), but lacks explicit guidance on when to use this tool over alternatives like apply_edits or render_document. No exclusion criteria or prerequisites are mentioned.

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

• render_documentA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It reveals the output format (base64) and that it creates files, but lacks details on side effects, authentication needs, rate limits, or any destructive behavior. For a write operation, this is insufficient.

  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 with no redundant words. It front-loads the core purpose and immediately follows with output and usage context. Every sentence 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?

  Given the tool's complexity (2 simple params, no output schema, sibling tools exist), the description is minimally adequate. It covers purpose, output format, and usage context, but lacks details on error handling, return value structure (beyond base64), or prerequisites.

  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 the baseline is 3. The description does not add significant meaning beyond the schema: it mentions 'structured spec' and 'Office bytes' but does not elaborate on the spec object structure or format details.

  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 'Render' and the resource 'structured spec into real Office bytes', and explicitly adds scope ('xlsx/pptx/docx') and output format ('base64'). It also distinguishes itself as the 'primary authoring path' among siblings.

  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 clear context for when to use the tool ('after an agent writes a spec') and positions it as the primary authoring path, but does not explicitly state when not to use it or compare it to alternatives like apply_edits or convert_document.

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

• apply_editsA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It states the tool returns a re-validated spec and that editing is lossless, but it does not disclose error handling (e.g., invalid ops), whether the original spec is mutated, or potential side effects.

  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 with no extraneous words. The first sentence states the core purpose, and the second adds relevant context about caller responsibility and lossless property. Efficient and front-loaded.

  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 three parameters and no output schema, the description explains the return value (edited, re-validated spec) and caller duties. It lacks details on error scenarios or confirmation of immutability, but is largely complete for a straightforward edit 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 description coverage is 100%, so the schema already documents all parameters. The description redundantly lists the ops format but adds no new meaning beyond the schema. Baseline score of 3 is appropriate.

  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 tool applies a list of edit ops (replace, set, append, remove) to a spec and returns the edited, re-validated spec. It distinguishes itself from sibling tools (convert, parse, preview, render) which do not modify the spec.

  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 the tool is for modifying a spec, but it does not explicitly state when to use it versus alternatives. It mentions that the caller re-renders the result, but provides no guidance on prerequisites or when not to use this tool.

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

• convert_documentA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It discloses the engine (LibreOffice-WASM) and return format (base64), but lacks details on size limits, timeouts, supported input formats, or error conditions. It provides some behavioral context but not comprehensive.

  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, no fluff. Key information is front-loaded (verb and resource) and every word adds value. Highly efficient.

  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 output schema, the description explains the return value (converted bytes as base64). It covers the conversion mechanism and fidelity aspect. Minor gaps: no mention of input format constraints or error scenarios, but overall sufficient for a relatively simple tool.

  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 providing example target formats (pdf, html, png) that go beyond the schema's single example, and clarifies that the input is base64-encoded. This enriches parameter understanding.

  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 tool converts a document to another format, with examples like pdf, html, png, and mentions using LibreOffice-WASM. It distinguishes from sibling tools (apply_edits, parse_document, preview_document, render_document) by specifying conversion as the core action.

  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 usage for fidelity-critical conversions without native LibreOffice, but it does not explicitly compare with siblings or provide when-to-use vs when-not-to-use guidance. Context is somewhat implied but not directly actionable.

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

• parse_documentA
  4.4/5.0
  Behavior4/5

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

  With no annotations, description carries full burden. It discloses that pptx/docx parsing will error and that xlsx parsing includes data and headers. Does not mention destructive actions, rate limits, or authentication, but the read-only nature is implied by 'read' verb.

  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 waste. Front-loaded with action and immediately addresses constraints. Every sentence provides essential information.

  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 two-param tool with no output schema, the description covers the core purpose, supported format, and error cases. Lacks explanation of what a 'spec' is, but this is likely understood from domain context.

  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%, but description adds context beyond schema by noting format support and that pptx/docx will error. This helps the agent understand the enum values behaviorally.

  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?

  Description clearly states verb 'Read' and resource 'exisiting file' into a spec, and specifies supported format (xlsx) and that pptx/docx will error. Differentiates from sibling tools like convert_document or preview_document by focusing on parsing back to spec.

  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 states current support is only for xlsx and that pptx/docx will error, providing clear when-to-use guidance. Does not explicitly name alternatives for pptx/docx, but the context of sibling tools implies they may handle those formats.

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