Server Quality Checklist

Tool Scores

• build_prompt_briefA
  3.7/5.0
  Behavior4/5

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

  Annotations already cover readOnly, openWorld, idempotent, and non-destructive behavior, so the description only needs to add beyond them. It adds the critical behavioral fact that the tool does not generate an image, and characterizes the output as deterministic with constraints and revision moves. This is useful context beyond the structured fields.

  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 the core action and output in the first sentence and a key limitation in the second. No filler or restatement of the title.

  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?

  The description neither explains the optional parameters nor describes the structure of the resulting brief, and there is no output schema to fill that gap. The phrase 'constraints and revision moves' hints at content but not at format or behavior. For a 6-parameter tool with one required field, more detail is needed for an agent to invoke it correctly.

  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 coverage is 0%, so the description carries the full burden, yet it only vaguely references the input as a 'rough image idea' (aligning with the required 'idea' parameter). It says nothing about the meaning, usage, or effect of style, useCase, exactText, aspectRatio, or referenceConstraints. This leaves most parameters semantically opaque.

  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 and resource: 'Turn a rough image idea into a structured, deterministic GPT Image 2 brief with constraints and revision moves.' It also explicitly distinguishes itself from image generation with 'This does not generate an image.' This clearly separates it from sibling retrieval tools like search_prompts and get_prompt.

  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 use case: when you have a rough image idea and need a structured brief. It does not, however, name any alternatives or state conditions for using search_prompts, get_prompt, or list_categories instead. The only exclusion is negative ('does not generate an image'), which is not enough to fully route an agent among siblings.

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

• search_promptsA
  3.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered externally. The description adds useful behavioral context by stating return content ('previews, media, categories, and canonical Image3 source pages') and noting it is free. No contradiction with annotations exists.

  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 exactly two sentences with no filler. The verb and resource are front-loaded, followed by return content and a brief cost/safety note. Every word earns its place.

  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?

  Despite the tool being relatively simple, the description omits all parameter semantics and provides no differentiation from siblings. With no output schema and no parameter descriptions, the definition is not complete enough for an agent to confidently call the tool correctly. Annotations cover the safety profile, but the remaining operational details are missing.

  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 carries the full burden of explaining parameters. It does not mention 'query', 'category', 'language', 'featuredOnly', or 'limit' at all; the word 'categories' in the return could even be confused with the 'category' filter parameter. This is a significant gap for an agent trying to construct an effective search.

  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 ('Search') and a specific resource ('Image3 GPT Image 2 prompt gallery'), and lists what is returned ('concise previews, media, categories, and canonical Image3 source pages'). This clearly distinguishes it from siblings like get_prompt, list_categories, and build_prompt_brief, which all have different actions.

  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 when to use this tool — when searching the prompt gallery is needed — but it never explicitly contrasts it with sibling tools or states when not to use it. No exclusions or alternative routing are provided, so the agent must infer the boundary between searching and getting a specific prompt or listing categories.

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

• list_categoriesA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and idempotentHint, so the description's 'Read-only' confirms rather than adds. It does add valuable context: 'free' signals no cost, and 'with counts' hints at the return shape beyond what annotations provide.

  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 followed by a short phrase. It is front-loaded with the core action and resource, and every word adds 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 read-only list tool with one optional parameter and rich annotations, the description is nearly sufficient. The absence of an output schema is partly mitigated by the mention of categories with counts, though a bit more detail about the language parameter's effect would make it fully complete.

  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 clarifies that language is optional and affects which categories are listed, but it does not explain what each enum value means, what 'all' includes, or what exactly the counts represent.

  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 the specific verb 'List' and the resource 'Image3 prompt categories', and adds the output detail 'with counts' plus an optional language filter. This clearly distinguishes it from sibling tools like search_prompts, get_prompt, and build_prompt_brief.

  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 use case is implied: if you need to enumerate prompt categories with counts, this is the tool. However, the description does not explicitly say when to choose this over alternatives or mention any exclusions.

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

• get_promptA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the description only needs to add value beyond safety. It does: 'sanitized' signals the returned prompt is processed/cleaned, and 'its media' discloses the response includes associated media. No contradiction between description and 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 sentences with no filler; the core action and output are front-loaded in sentence one, and sentence two provides routing guidance. Every word earns its place.

  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 one-parameter read-only tool with rich annotations, the definition covers the essential operation, the source of valid inputs, and the basic return shape (sanitized prompt plus media). No output schema exists, so the mention of return contents is the right compensation. Minor omissions like error behavior and pagination are not material 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?

  Schema description coverage is 0%, so the description carries the full burden for the only parameter. It clarifies that slugOrId accepts either a slug or an id and that valid values come from search_prompts, which is meaningful beyond the bare string type. It stops short of describing the expected slug format or how id and slug resolution differ, but for a single simple parameter this is solid.

  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 ('Get'), names the resource (a prompt from Image3), and adds qualifying detail: it returns one complete sanitized prompt and its media. The second sentence tells the agent to use an identifier from search_prompts, which distinguishes this tool from search operations. Nothing is left ambiguous about what the tool fetches.

  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 states that the identifier must come from search_prompts, establishing the correct workflow — search first, then get. This is clear usage context, though it does not spell out when-not-to-use cases or name alternative tools beyond the implicit search_prompts dependency. A 5 rating would require explicit exclusions, so this lands at 4.

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