Server Quality Checklist

Tool Scores

• create_presentation_from_topicA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It discloses the async behavior: returns a job ID, poll via check_job_status, then use docurl. It does not detail failure modes, authentication needs, or rate limits, but the core behavioral flow is well explained.

  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 four sentences, each adding essential information: what the tool does, when to use it, how the async flow works, and an alternative. No fluff, and critical details are 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?

  For a complex tool with 9 parameters, no annotations, no output schema, and sibling tools, the description provides a complete picture: usage context, async flow with polling, and alternative tool. It covers the key aspects an agent needs to invoke and manage the tool correctly.

  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 already provides 100% coverage with descriptions for all 9 parameters. The description does not add additional meaning beyond the schema—it mentions topic, slideCount, etc., but that matches schema descriptions. 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?

  The description clearly states the tool's action: 'Generate a full AI-powered presentation from a topic or brief.' It specifies the resource (presentation) and scope (from topic/brief), and distinguishes from sibling tool create_single_slide by noting when to use the alternative.

  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?

  Explicit when-to-use: 'Use when the caller has a subject line, headline, or short brief and wants a complete deck.' It also provides an alternative: 'For a single hero slide instead of a deck, use create_single_slide.' Additionally, it explains the async processing flow and directs to check_job_status for polling.

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

• check_job_statusA
  4.6/5.0
  Behavior5/5

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

  Discloses that it's safe to call repeatedly, does not consume job state. Details response fields for each status (completed, failed, processing). No annotations provided, so description carries full burden and does it well.

  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?

  Paragraph is well-structured and front-loaded with purpose. Each sentence adds value. Could be slightly more concise but is efficient overall.

  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 simplicity (one param, no output schema), the description covers purpose, usage, behavior, and response fields completely. No gaps.

  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?

  Only parameter jobId has schema description 'The job ID returned from a create_* call when immediatePollUrl=true or when callback_url was omitted.' Schema coverage 100%, but description adds context about where jobId comes from, adding value beyond 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?

  Description clearly states 'Poll for the result of an async presentation job' and specifies it's used after any create_* call that returned a jobId. This distinguishes it from sibling create 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 says 'Use after any create_* call that returned a jobId' and provides recommended polling cadence (55-60s first, then 30-35s). No explicit when-not, but context is clear.

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

• create_presentation_from_fileA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description provides key behavioral details: max size 5 MB, supports preservation modes, returns a job ID, and requires polling. Lacks mention of any destructive side effects, but creation tools typically imply mutation.

  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 sentences cover all critical points: purpose, usage guidance, constraints, and follow-up steps. No wasted words.

  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 12 parameters (mostly optional) and no output schema, the description covers essential behavioral aspects: size limit, return type, polling, and references to sibling for options. Could mention error handling or example, but sufficient for an experienced 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?

  Schema coverage is 100%, baseline 3. Description adds value beyond schema: size limit for file_data, match requirement for mime_type, references to sibling tool for preservationMode and exportType options, and notes on slideCount dependency.

  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 'Convert an uploaded document ... into a presentation,' listing supported file types. It distinguishes from sibling tool 'create_presentation_from_content' by noting the different input method.

  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: 'Use when the caller already has a source document.' Provides clear alternative: 'For pasted raw text use create_presentation_from_content.' Also mentions polling via check_job_status.

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

• create_presentation_from_contentA
  4.7/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It discloses that the tool returns a job ID and suggests polling check_job_status, but does not cover auth requirements or potential side effects. Still, the async nature is clearly communicated.

  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?

  Single paragraph with front-loaded purpose, each sentence earns its place. No redundancy or verbosity.

  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?

  Covers main purpose, usage, parameter behaviors, return value (job ID), and sibling distinction. Lacks examples for callback_url or further detail on output, but overall sufficient for an async creation tool.

  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 100%, but description adds significant extra context: details on preservationMode (which modes require slideCount), topic override vs instruction, and cross-reference to create_presentation_from_topic for exportType options.

  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 transforms raw text into a polished presentation, specifies the use case (caller has prose/notes), and distinguishes from sibling tools like create_presentation_from_file for file uploads.

  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 use (when caller has prose/notes) and when not (for file uploads use create_presentation_from_file). Also explains preservationMode behaviors and dependencies.

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

• create_single_slideA
  4.7/5.0
  Behavior5/5

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

  Discloses async behavior (returns job ID, poll check_job_status), typical completion time (20-40 seconds), and faster-than-full-deck nature. No annotations provided, so description carries full burden and does well.

  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, front-loaded with purpose, no redundant words. Every sentence adds value: purpose, use cases, sibling alternative, async mechanics, and speed comparison.

  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?

  Covers purpose, usage, async behavior, polling instruction, timing, and sibling distinction. Without output schema, description appropriately explains what to expect (job ID) and how to use it. 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.

  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 parameters thoroughly. Description adds context about return value (job ID) but does not add new parameter-specific semantics beyond schema. 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?

  Clear verb 'Generate' and specific resource 'a single AI-designed slide from a topic'. Lists use cases (hero slides, social-media graphics, one-off visuals) and distinguishes from sibling tool create_presentation_from_topic for multi-slide decks.

  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 (hero slides, social-media graphics, one-off visuals) and when not (full multi-slide deck, directing to create_presentation_from_topic). Clear guidance.

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