Server Quality Checklist

Tool Scores

• get_newsA
  4.5/5.0
  Behavior4/5

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

  Annotations already cover read-only, idempotent, non-destructive behavior. The description adds the limitation that only the current feed window is available and includes a citation requirement when repeating stories, providing useful context beyond the 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?

  Three sentences, each adding value: the main action, feed details, and constraints/citation. No filler, front-loaded with the core purpose.

  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?

  With rich annotations and an output schema, the description covers usage, feed semantics, a limitation, and citation guidance. It is sufficiently complete for an agent to decide when and how to use the 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%, but the description enhances the feed parameter by explaining what 'all' mixes, and gives concrete category examples (Manga, Anime) beyond the schema's 'matched case-insensitively'.

  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 reads the latest Anime News Network stories from their RSS feeds, using specific verbs and resource. It distinguishes from sibling tools by emphasizing the feed window and content mix, making its scope unambiguous.

  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 clear context on feed options ('all' mixes, 'news'/'reviews' narrower) and an explicit exclusion ('no way to reach older stories through this tool'). However, it does not name sibling tools as alternatives, so it lacks full when-to-use vs. alternative guidance.

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

• search_titlesA
  4.5/5.0
  Behavior4/5

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

  Annotations already cover readOnly/openWorld/idempotent/non-destructive, so the bar is lower. The description adds useful behavioral specifics: substring matching, the 'compact row' fields (id, kind, type, name, precision, vintage), and the limitation to title-only search. This goes beyond the annotation safety profile.

  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, no filler. It front-loads purpose, then covers output format, usage workflow, and limitations. Every sentence carries information without redundancy.

  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 search tool with a rich output schema and straightforward params, the description covers purpose, return values, workflow with get_title, matching behavior, and search scope limitations. The output schema handles field details, so nothing critical is missing.

  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 3 is appropriate. The description reinforces the query param's substring behavior but does not add new semantics for kind or limit beyond what the schema already explains.

  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 'Search the Anime News Network encyclopedia for anime and manga by title' – a specific verb, resource, and scope. It further distinguishes from siblings by noting 'This searches titles only. It cannot find an entry from a plot detail, a character or a studio.'

  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 gives clear follow-up guidance: 'Use the id and kind with get_title to read the full entry.' It also advises on query tuning: 'Matching is on substring... narrow the query rather than raising limit.' It explicitly states what the tool cannot do, preventing misuse.

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

• list_recentA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare this as read-only, idempotent, and non-destructive, so the description doesn't need to repeat that. It adds valuable behavioral context by stating that 'starts_with' switches to alphabetical browsing, is restricted to anime/manga, and that rows carry an id usable with 'get_title'. This goes beyond what annotations alone provide, though it doesn't describe pagination details or output format, keeping it at a 4.

  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 three sentences long, front-loaded with the primary purpose, and every sentence earns its place. It mixes listing behavior, a special mode, and alternative tool guidance without redundancy or verbosity.

  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 an output schema, comprehensive annotations, and a fully described input schema, the description covers the essential contextual gaps: the difference between listing and search, the chaining to get_title, and the constraints of starts_with. There is no missing critical information for an agent to invoke this tool correctly.

  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 every parameter already described. The description still adds meaning by explaining how 'starts_with' affects behavior (alphabetical browse and anime/manga only) and highlighting the id's role in chaining to 'get_title'. This enhances the schema's bare definitions, justifying a score above the baseline.

  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 purpose: listing recent additions to the Anime News Network encyclopedia, with options for anime, manga, people, or companies. It distinguishes itself from siblings by explicitly saying 'This is a listing, not a search' and naming the alternative 'search_titles', plus references to 'get_title' for follow-up.

  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 gives explicit usage guidance: when to list recent additions, how to switch to alphabetical browsing via 'starts_with', which kinds are supported for that mode, and when to use 'search_titles' instead. It even explains that returned IDs can be passed to 'get_title' for specific kinds, providing clear alternatives and context.

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

• get_titleA
  5/5.0
  Behavior5/5

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

  Beyond the readOnly/idempotent annotations, the description adds crucial behavioral details: the record can be very large, sections are opt-in, 'basic' covers specific fields, and plot summaries are paginated with truncated/offset/next_offset. This meaningfully expands on annotation hints.

  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 compact yet dense, with front-loaded purpose and no redundant phrases. Each sentence earns its place: purpose, prerequisite, opt-in sections, basic fields, and pagination. 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?

  Despite having an output schema, the description covers the essential operational context: how to start, what to request, and how to handle pagination. It is complete for a read tool with well-annotated safety and idempotency.

  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?

  The schema already covers parameters (100% coverage), but the description adds value by explaining the 'sections' enum and what 'basic' includes, and by contextualizing 'offset' with pagination. This goes beyond the schema's property descriptions.

  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 'Read' with a clear resource ('Anime News Network encyclopedia entry') and the key identifier 'by id'. It also explicitly instructs to obtain id/kind from search_titles, distinguishing it from sibling tools like search_titles and list_recent.

  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 workflow guidance: 'Get the id and kind from search_titles first' directly tells the agent when to use this tool versus search_titles. It also gives parameter usage advice ('Sections are opt-in', 'ask only for what you need') and pagination instructions for repeated calls.

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