Server Quality Checklist

Tool Scores

• get_reviewsA
  4.7/5.0
  Behavior5/5

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

  Annotations already mark this as read-only, idempotent, and non-destructive, so the description adds non-redundant details: Metacritic's fixed-sample limitation, no pagination beyond the sample, critic/user score scale differences, and the presence of publication/link for critic reviews. These are exactly the behavioral traits an agent needs to set expectations.

  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?

  Five sentences, all substantive. Begins with the purpose, then prerequisites, then constraints, then scoring caveat. No filler or repetition of schema 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?

  Combined with the rich input schema and output schema, the description covers the tool's usage workflow, sample limitations, and score handling. It leaves no critical behavioral gaps for an autonomous 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 covers 100% of parameters, so the baseline is 3. The description enriches this by explaining offset's limitation ('The sample itself cannot be paged past') and the meaning of sentiment ('which Metacritic groups itself'), adding operational nuance beyond the schema's raw definitions.

  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 opens with 'Read individual reviews of a Metacritic entry, from critics or from users' – a specific verb and resource that clearly differentiates from sibling tools (search_titles, browse_titles, get_title). It also states the prerequisite of obtaining slug and kind from search_titles, reinforcing the tool's role.

  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 instructs 'Get the slug and kind from search_titles first', providing a clear prerequisite. It also warns about the fixed sample and inability to page past it, and cautions against averaging critic and user scores. It doesn't name alternative tools directly, but the usage context is unambiguous.

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

• browse_titlesA
  4.8/5.0
  Behavior5/5

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

  The description adds substantial behavioral context beyond the annotations: score scales (100 for critics, 10 for users), approximate paging with possible duplicate entries across pages, and the all-time ranking bias toward older titles. These are non-obvious traps the agent must account for.

  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?

  Seven sentences are tightly structured: purpose and intended use first, then filtering, then result interpretation, then paging caveats. Every sentence adds value and there is no redundant phrasing.

  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 moderate complexity, read-only annotations, and existing output schema, the description fully covers what the tool does, when to use it, how to filter, how to interpret scores, and how to handle paging edge cases. No crucial information is missing.

  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 the description enriches the parameter meanings: it explains what each sort option yields, instructs genre to be a single name like Horror, and warns that offset paging is approximate so deduplication by slug is needed. This is more than the schema descriptions provide.

  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 opens with a specific verb and resource: 'List films, shows or games by score, by release date or by current popularity.' It clearly distinguishes this browsing tool from siblings by stating it is for when there is no specific title to look up, unlike search_titles or get_title.

  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 says 'Use this when there is no specific title to look up' and lists example intents (best rated, newest, what people are looking at now). It does not directly name sibling tools as alternatives, but the exclusion is clear enough given the visible sibling list.

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

• get_titleA
  4.8/5.0
  Behavior5/5

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

  Adds valuable behavioral details beyond the read-only/idempotent annotations: sections gate each other, critic and audience scores use different scales (never compare), where_to_watch has an extra cost and only applies to films/shows, and long descriptions paginate with offset/next_offset. 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?

  The description is compact yet information-dense. It front-loads the core action, then efficiently explains sections, behavior, and pagination without 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?

  Given the tool's complexity (multiple optional sections, pagination, cost implications), the description covers all essential behaviors and gives clear guidance. The output schema exists, so return values are documented separately, making this description fully adequate.

  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?

  Despite 100% schema coverage, the description adds rich meaning to the sections parameter (defaults, gating, costs), to offset (pagination with truncated/next_offset), and to the semantics of scores (separate scales). This goes far beyond the schema 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?

  States unambiguously that it reads a single Metacritic entry by slug and kind, with identifiers coming from search_titles. This differentiates it from siblings that search or browse.

  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: identifiers come from search_titles, sections are opt-in with a default set, and pagination is explained for long descriptions. Does not explicitly name alternatives like get_reviews, but the usage context is strong.

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

• search_titlesA
  4.9/5.0
  Behavior5/5

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

  Beyond the annotations (readOnly, openWorld, idempotent), the description discloses several behavioral traits: rows are compact and include Metascore but not audience score; there is no paging and results always start from the most relevant match; and the search is restricted to titles only. These details significantly exceed the annotation baseline.

  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 five sentences each carrying distinct information: purpose, return contents, exclusions and alternatives, paging behavior, and search scope. It is front-loaded with the core action and avoids any filler or repetition.

  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 moderate complexity, the presence of an output schema, and rich annotations, the description covers all essential aspects: what it searches, what rows contain, what they lack, how to get missing data, limit/paging behavior, and the limitation to title-based search. No significant gaps remain.

  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?

  The input schema already has high coverage (100%) with clear parameter descriptions. The description adds meaningful context for 'limit' by explaining 'There is no paging: limit is the only lever, and results always start from the most relevant match,' which gives behavioral nuance not present in the schema description. Baseline is 3, so the added semantics justify a 4.

  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 'Search Metacritic for films, shows and games by title' – a specific verb and resource. It distinguishes itself from siblings by explicitly noting that it searches titles only and cannot search by plot, person, or studio, while also referencing get_title, get_reviews, and browse_titles for other needs.

  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?

  It gives explicit when-to-use guidance: 'Search rows carry no audience score: use get_title for that, or browse_titles, which does return it' and 'Use the slug and kind with get_title for the full entry, or with get_reviews for what critics wrote.' It also states limitations ('This searches titles only. It cannot find an entry from a plot detail, a person or a studio'), providing clear when-not-to-use context.

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