Server Quality Checklist

Tool Scores

• resolve_musicA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool 'returns ranked results' and explains the ranking criteria: 'trust × price × availability, never by commission.' It does not cover errors, rate limits, or authentication, but for a read-only lookup tool the disclosed ranking behavior is substantive.

  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 with no filler: purpose, result coverage, usage trigger, and ranking behavior are all stated efficiently. It is front-loaded with the core action and each subsequent sentence adds distinct value.

  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?

  The tool has one required parameter, and the schema thoroughly documents its format and edge cases. The description covers scope, ranking behavior, and when to use it, with no output schema requiring explanation of return values. Nothing essential for correct invocation 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 the schema already fully documents the single 'slug' parameter, including format, non-Latin scripts, accent folding, and percent-encoding guidance. The description adds no parameter-specific detail, so it stays at the baseline for a fully documented 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 opens with a specific verb and resource: 'Find where to stream, buy, or collect a song or album.' It clearly distinguishes this tool from siblings like resolve_artist, resolve_game, find_product, and discover_music by defining the music-lookup scope and the categories of results (streaming, purchase, physical media).

  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 an explicit trigger: 'Use when a user asks about music — whether they want to listen, own digitally, or find a collector edition.' It does not explicitly name sibling alternatives or state when not to use the tool, but the usage context is clear enough for an agent to select it.

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

• resolve_gameA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of disclosure. It transparently notes the tool is currently non-functional, returning a 'coming soon' message, which is a key behavioral trait. However, it does not explicitly mention read-only nature or other side effects.

  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 and well-structured: a single sentence for purpose, a second for details, and a crucial note about current status. Every sentence adds value without repetition.

  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 no output schema, the description explains the return format (ranked results with prices, editions, DLC info) and the current limitation. It covers the stores list. It is mostly complete but lacks mention of error handling or data freshness.

  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 schema coverage is 100% for the single required parameter. The description adds no additional meaning beyond the schema, repeating the slug format and example from the schema. Thus, the baseline score of 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 purpose: finding where to buy a video game at the best price across specific trusted stores. It distinguishes itself from siblings by targeting games versus music.

  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 not only explains when to use the tool (for game purchases) but also advises when not to use it (for music queries) and provides alternatives (`resolve_music` or `find_product`), fulfilling the guidelines dimension well.

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

• resolve_artistA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full transparency burden. It clearly frames the operation as a read ('Get') and describes what the response contains: genres, every release, and slugs. It also adds a useful behavioral nuance: physical formats live at the album level, so this is the route to collector editions. It doesn't cover every possible edge case, but it discloses the key behavioral traits an agent needs.

  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 rich: three sentences, no filler, and the core purpose is front-loaded. Every sentence earns its place—purpose, usage examples, return-value summary, and the album-level physical format nuance all contribute unique value.

  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 single-parameter tool with no output schema, the description is remarkably complete: it states what the tool returns, how the output relates to resolve_music, and why physical-format seekers should use this route. An agent has enough context to select and invoke the tool correctly without opening sibling schemas.

  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 fully documents the slug parameter, including accepted forms. The description mentions slugs but adds no new parameter semantics beyond what the schema provides. This meets the baseline of 3 but does not exceed it.

  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: 'Get an artist's profile and full discography.' It also clearly separates this from song-level tools by saying it covers a 'body of work rather than one song,' making the tool's role obvious even before considering 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?

  The description gives explicit when-to-use guidance with concrete examples: 'what albums has Stromae released', 'show me Radiohead's discography'. It names resolve_music as the alternative for turning slugs into links and implies song-level requests should go elsewhere, giving both positive and negative use cases.

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

• find_productA
  4.6/5.0
  Behavior4/5

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

  No annotations are provided, so the description must fully disclose behavior. It explains auto-detection of product category, routing to resolvers, and states which categories are live and which are rolling out. It lacks explicit details on authentication or rate limits, but for a non-destructive routing tool, this is reasonably transparent.

  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 and well-structured, starting with the core purpose ('Smart router'), then detailing supported categories and usage guidance. Every sentence adds value without redundancy.

  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 the tool's complexity (routing, multiple categories) and lack of output schema, the description adequately explains behavior, status, and when to use. It could mention fallback behavior for unsupported categories, but overall it is complete enough for an agent to use 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?

  The input schema has 100% coverage with descriptions for both parameters. The description adds context by explaining the 'query' parameter with natural language examples and the 'category' enum with the 'auto' default. This exceeds the baseline of 3 by providing meaningful usage context.

  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 it is a 'Smart router' that finds the best place to stream, buy, or collect products. It specifies the product categories (music, games, etc.) and clearly distinguishes from sibling tools like discover_music, resolve_game, and resolve_music.

  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 provides explicit guidance: 'Use this when the query is ambiguous or when music could be streamed, purchased digitally, or found on physical media.' It also explains the category parameter's auto-detect behavior, helping the agent decide when to use this tool over alternatives.

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

• discover_musicA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description carries the full disclosure burden and does so well: it says the tool returns walls with slugs, that entries can be expanded, that streaming/purchase links require resolve_music, that year mode returns snapshots, and that results are ranked by editorial pinning and refresh freshness, not commission. These behavioral details go beyond any structured field.

  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 about six purposeful sentences with the core action and scope front-loaded, then examples, return semantics, and a ranking note. No filler; each sentence adds operational or behavioral information an agent needs.

  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 browse/discovery tool with four optional parameters and no output schema, the description covers how results are shaped (walls, entries, snapshots), how to drill in, how to resolve external links via a sibling, and ranking intent. There is no missing operational context an agent needs to invoke it 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%, so the baseline is 3, but the description adds value by explaining the wall-slug flow, that snapshot slugs should be passed back as wall, and that position 1 is the number one. It also frames year as the past-archive mode and chamber as the browse mode in user terms, supplementing but not repeating 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?

  States a specific action ('Browse curated music collections') with concrete resource types (charts, genre walls, moods, editorial playlists, artist spotlights, historic charts). It explicitly distinguishes exploration from looking up a specific song or album and names the sibling 'resolve_music' for fetching links, so an agent can separate it from 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?

  Gives an explicit use-case rule ('Use when a user wants to EXPLORE music rather than look up a specific song or album'), illustrative example queries, and a follow-up path (pass returned wall slugs back as the wall argument; use resolve_music for page links). This is clear when-to-use and alternative guidance.

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