Server Quality Checklist

Tool Scores

• citeA
  4/5.0
  Behavior2/5

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

  No annotations are provided, so the description must fully disclose behavioral traits. It only describes output styles but does not mention idempotency, side effects, authentication needs, or rate limits. For a read-like operation, this is a notable gap.

  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, front-loaded with the main purpose, and every word adds value. No redundancy or unnecessary detail.

  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 tool with two parameters and no output schema, the description covers the essential purpose and parameter variations. It omits details about the return format (e.g., plain text vs. JSON) but is otherwise complete for typical use.

  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?

  While schema coverage is 50%, the description adds meaning to the 'style' parameter by explaining what each enum value produces ('full' includes artist, title, etc.; 'caption' for image captions; 'short' for inline references). The 'id' parameter is adequately described in 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 'Render a citation for an artwork' and lists three distinct styles ('full', 'caption', 'short'), making the tool's purpose specific and differentiating it from sibling tools like 'discover_random' or 'search_artworks'.

  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 explains each style's purpose ('full' includes all fields, 'caption' for image captions, 'short' for inline references), providing clear context for when to use each variant. However, it does not explicitly state when not to use this tool or alternative tools, though sibling tools are sufficiently different.

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

• get_artworkA
  4.2/5.0
  Behavior3/5

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

  With no annotations, description states read-only fetch but does not disclose error behavior or rate limits; adequate for simple fetch.

  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 sentence, no redundancy, efficiently conveys essence.

  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 simple 1-param tool, description explains input but omits return value details; acceptable for its simplicity.

  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 already covers parameter; description adds format details and example, enhancing clarity beyond schema alone.

  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 specifies action (fetch), resource (single artwork), and mechanism (by normalized ID). Distinct from siblings: search_artworks returns multiple, others are different in scope.

  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?

  Provides format example, implicitly conveys use case (have an ID), but lacks explicit when-to-use vs alternatives like search_artworks.

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

• search_artworksA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It discloses that ambiguous records are excluded by default, that rights verification is applied, and that records with no parseable date are excluded when year bounds are set. The parameter description for has_image also notes museum-specific behavior (Met only exposes images-only search server-side). This is good but could mention authentication or rate limits.

  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 concise, with two sentences front-loading the main purpose and then adding a usage example. No unnecessary words or repetition.

  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 has 6 parameters and no output schema, the description covers core functionality and filtering but lacks details on return format, pagination, or ordering. It is adequate but not fully complete for a search 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 high (83%), so baseline is 3. The description adds value by giving a specific date-range usage example ('Dutch genre painting 1640–1680') that illustrates the year_min and year_max parameters. It also provides context about rights verification, though not directly per parameter.

  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 searches across registered open-access museum collections and returns artwork records with rights verification. It uses specific verb and resource, distinguishing it from siblings like get_artwork (retrieval by ID) and discover_random (random selection).

  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 a concrete example of when to use the date-range filter ('researcher queries like Dutch genre painting 1640–1680'), which helps with usage context. However, it does not explicitly state when not to use this tool or contrast it with sibling tools.

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

• discover_randomA
  4.8/5.0
  Behavior5/5

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

  No annotations exist, so description fully discloses caching behavior, auto-seeding on cold cache with region/period, and hint when no constraints. 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?

  Description is concise yet comprehensive, front-loaded with purpose followed by usage scenario and technical details. Every sentence contributes meaningfully.

  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 exists; description implies return of an artwork but doesn't detail format. However, it thoroughly covers parameters, caching, and constraints, making it sufficiently complete for a random-selection 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. Description adds value by explaining how parameters (region, period) trigger auto-seeding and notes exact matching for not_artist, going 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?

  The description explicitly states the tool picks a random artwork from a local cache matching constraints, differentiating it from search_artworks and other siblings.

  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?

  Provides clear when-to-use guidance (breaking repetitive search), includes a concrete example scenario, and explains behavior with and without constraints, suggesting alternatives.

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

• list_traditionsA
  4.9/5.0
  Behavior5/5

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

  No annotations provided; description fully discloses behavior: lists from non-expired cached records, returns hint on empty cache, specifies return structure.

  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 concise, front-loaded sentences, each adding essential information without wordiness.

  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, description covers purpose, usage, return shape, and edge case (empty cache) comprehensively.

  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, so baseline is 4. Description adds no parameter info, which 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 states it lists regions and periods from cached records with counts, distinguishing it from siblings like search_artworks by noting it's a meta-tool.

  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 to run search_artworks first if cache is empty, and clarifies it's not a search trigger, providing clear when-to-use guidance.

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