Server Quality Checklist

Tool Scores

• render_slidesA
  4.2/5.0
  Behavior4/5

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

  Annotations indicate idempotentHint=true. Description adds that it accepts html or htmlPath, falls back to cached HTML, and returns file paths on disk. Warns about pptxMode 'native' not preserving design, 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Front-loaded with core purpose. Each sentence adds value (formats, parameters, workflow rules). Could be slightly more concise but is well-structured and efficient.

  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?

  Good usage guidelines and behavioral context for a 14-param tool. However, missing details on return value structure (e.g., array of paths) since no output schema exists. Workflow dependencies are well explained.

  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 covers 100% of 14 parameters with descriptions. The description lists many parameters but adds little extra meaning beyond their names; workflow context is provided but not parameter-specific. Baseline 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?

  Description clearly states the action 'render' with specific output formats (PDF, WebP, PNG, PPTX). It distinguishes from siblings by being the 'Final' step, contrasting with create_slides and discover_themes.

  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?

  Explicitly forbids calling render_slides in the same turn as create_slides. Provides clear workflow: for existing HTML file, call directly; for full workflow, require discover_themes and create_slides first, and only after user confirmation.

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

• create_slidesA
  4.3/5.0
  Behavior5/5

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

  Annotations indicate idempotentHint=true and destructiveHint=false. The description adds crucial behavioral details: the mode behavior (full HTML vs JSON), the requirement for prior steps, and the post-call action (show htmlPath, stop, ask confirmation). It also warns against prematurely calling render_slides. No contradictions with annotations.

  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 well-structured with important information front-loaded and emphasized (IMPORTANT, REQUIRES, MUST, STOP, DO NOT). However, it is slightly verbose, repeating some points (e.g., mode guidance appears twice). A more concise version could remove redundancy while retaining 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 the tool's complexity (8 parameters, multiple prerequisites, conditional modes), the description covers workflow, mode selection, and post-call actions. It lacks an explicit statement of the return value (htmlPath is mentioned but not as a return field). Error conditions and responses are not addressed. Still, it provides sufficient context for correct usage.

  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 baseline is 3. The description adds some meaning beyond schema for mode (explaining quality trade-off) and implies conditions for html and slides. However, themes, orientation, width, height, and brandName are not elaborated beyond the schema. The description does not significantly increase understanding of parameter semantics.

  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 starts with 'Create slides,' clearly indicating the action and resource. It further details mode options and prerequisites, distinguishing it from siblings like discover_themes and render_slides. However, it could be more explicit about what 'create slides' entails (generating HTML slides) and differentiate from edit_slides.

  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 provides excellent usage guidance: it specifies when to use each mode (default vs token_saver), mandates that discover_themes must be called first and the user must confirm the data outline, and strictly instructs not to call render_slides until user confirmation. This clearly separates this tool from its siblings.

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

• health_checkA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and not destructive. The description adds specific behavioral context (launch verification) beyond what annotations provide, without contradiction.

  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 concise, front-loaded sentences that each carry essential information: what the tool does and when to use it. No extraneous content.

  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 zero parameters and no output schema, the description fully covers the tool's purpose and usage context. Annotations provide safety guarantees. Complete for this 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?

  No parameters exist, so the baseline is 4. The description does not need to add parameter 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 uses a specific verb 'Verify' and identifies the resource 'Puppeteer/Chromium can launch'. It clearly distinguishes this diagnostic tool from the slide and theme tools.

  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 'Use when render fails', providing clear context for when to invoke this tool. Could mention when not to use, but the guidance is sufficient for a simple diagnostic.

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

• discover_themesA
  4.6/5.0
  Behavior4/5

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

  Annotations already indicate read-only, idempotent, non-destructive. Description adds workflow context: returns themes, orientation, etc., and is mandatory first step. No contradictions.

  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?

  Four sentences, front-loaded with most critical info (mandatory first step). Every sentence adds distinct value with specific do's and don'ts.

  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?

  No output schema; description lists return types (themes, modes, formats) but lacks exact structure. However, given the interactive workflow, description sufficiently supports agent decision-making.

  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?

  Input schema has 0 parameters with 100% coverage. Description adds no parameter info but none needed. Baseline score of 4 for zero-parameter tool.

  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 identifies tool as mandatory first step that returns themes and other options. Distinguishes from sibling tools by stating all other tools reject until this is called.

  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?

  Explicitly states when to use (first step), provides specific instructions on using native selector prompts, forbids certain actions (asking slide count), and outlines post-call workflow.

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

• edit_slidesA
  4.7/5.0
  Behavior4/5

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

  Annotations indicate readOnlyHint=false and destructiveHint=false, but description adds context: reads from cache or htmlPath, saves updated HTML, returns new htmlPath, and estimates token savings. It transparently describes behavior 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?

  Concise and well-structured: starts with purpose and efficiency claim, then lists operations in bullet format, and ends with clear behavioral instructions. Every sentence adds value.

  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?

  Even without an output schema, the description covers return value (new htmlPath) and behavior (caching, fallback). It provides enough context for correct invocation across all operations.

  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 descriptions for all parameters. The description further clarifies payload formats for each operation and slideIndex requirements, adding utility beyond the 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 the tool is for 'Token-efficient partial edits on a previously-generated HTML deck', distinguishing it from sibling tools like create_slides and render_slides. It lists specific operations, 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 Guidelines5/5

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

  Explicitly instructs to use this instead of regenerating the whole deck for small changes and provides a clear stop condition after editing: 'show the htmlPath as a preview artifact and STOP — do NOT call render_slides until the user confirms.' No ambiguity.

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

• list_themesA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and idempotentHint. Description adds that it returns tiered catalog (primary/secondary) and instructs models not to truncate. This adds value beyond annotations, though annotations cover core behavioral traits.

  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?

  Three sentences, each essential: purpose, usage guidance with sibling differentiation, and a behavioral constraint. Front-loaded with key info. No wasted words.

  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 zero-parameter listing tool with good annotations and no output schema, the description provides enough context: what it lists, when to use, output structure (tiered catalog), and behavior (no truncation). Complete enough for effective agent invocation.

  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?

  No parameters in schema; baseline is 4. Description does not need to add param information. No additional details about parameters are necessary and none are missing.

  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?

  Clearly states it lists themes (8+), is idempotent and read-only, and distinguishes from sibling discover_themes which starts a workflow. Uses specific verb and resource.

  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?

  Explicitly says when to call ('any time user asks what themes are there? mid-conversation') and that unlike discover_themes it does not start a slide-creation workflow, naming the alternative.

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