Server Quality Checklist

Tool Scores

• find_gastronomyA
  4/5.0
  Behavior3/5

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

  With no annotations, the description discloses some behavioral traits: it returns a formatted narrative list and notes world-specific geocoding for near (earth-313 vs bral). However, it does not explicitly state safety, sorting, or error behavior, leaving room for more transparency.

  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 well-structured with a clear purpose sentence, a bulleted parameter list, and a return statement. Every element serves a purpose, and it is concise despite covering seven parameters.

  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?

  All seven optional parameters are meaningfully described, return behavior is stated, and world-specific nuances are provided. Given the moderate complexity and presence of an output schema, the description is complete enough for an agent to invoke the tool correctly.

  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 has 0% description coverage, but the description fully compensates by explaining every parameter, including examples for cuisine and features, defaults for radius_m and max_results, and the relationship between near and lat/lon.

  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 as finding restaurants, food stalls, and gastronomy places in the current world. This uses a specific verb (find) and resource (gastronomy places), distinguishing it from sibling tools like find_accommodations and find_events.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  There is no guidance on when to use this tool versus alternatives such as find_accommodations or find_events. The only usage-related note is that lat/lon is an alternative to near, which addresses parameter selection rather than tool selection.

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

• find_accommodationsA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full transparency burden. It discloses that 'near' is geocoded differently per world, that some parameters are ignored for bral, and that results are returned as a formatted narrative list. It does not mention potential side effects, rate limits, or error handling, but for a read-only search tool this is adequate and exceeds minimal expectations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is organized with a clear main sentence followed by a bullet-like parameter list. It is longer than typical but each line adds value, especially the world-specific enumerations. Some redundancy exists (e.g., repeating 'earth-313 only' for multiple params) but the structure is scannable and front-loaded with the core purpose.

  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?

  The tool has 9 parameters, two world-specific variants, and no schema descriptions, yet the description covers parameter semantics and return format. It does not address edge cases like conflicting near vs lat/lon, but an output schema exists and the narrative return type is mentioned. This is highly complete for a search tool of this complexity.

  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 description coverage is 0%, so the description fully compensates by explaining every parameter: near (geocoding behavior), lat/lon as alternatives, radius_m default, features with per-world option lists, category behavior, date range constraints, and max_results default. This adds substantial meaning beyond the bare schema types.

  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 accommodations in the current world.' It clearly distinguishes from sibling tools like find_events and find_gastronomy by focusing on lodging and location-scoped search. The scope 'current world' ties it to the world context shared with set_world, avoiding confusion.

  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 clear usage context by explaining world-specific parameter behavior (earth-313 vs bral), such as which features are valid and when category is ignored. It implies when to use this tool (accommodation search) but does not explicitly contrast with alternatives like find_events. Nevertheless, the parameter guidance serves as strong usage direction.

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

• describe_worldA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly states a read-only action ('Return a narrative description') and does not contradict any annotations. It could add more context (e.g., that it reflects the current world state set by set_world), but the behavior is sufficiently transparent for a zero-parameter read tool.

  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, well-structured sentence that front-loads the action ('Return a narrative description') and packs essential information (current world, data availability, query guidance) without any fluff. Every word earns its place.

  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 simplicity (0 parameters, no nested objects, output schema present), the description is complete. It tells the user enough to understand what they will get (narrative description, data overview, query instructions) and is contextually sufficient for a meta-level 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?

  The tool has zero parameters, so the baseline is 4. The description adds no parameter-specific semantics, but that is not needed here. It appropriately focuses on the tool's purpose rather than parameter details.

  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 function: returning a narrative description of the current world, including available data and query methods. It distinguishes itself from sibling tools like find_accommodations and set_world by being the meta-level tool for understanding the world state, using the specific verb 'Return' and a clear resource.

  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 implicitly indicates usage: the user should call this tool to learn about the world and how to query it before using specific find_* or set_world tools. However, it does not explicitly state 'use this first' or provide alternatives/exclusions, so it stops short of a full 5.

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

• set_worldA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It explicitly states the persistent side effect ('for all subsequent queries'), lists available world options, and notes the return behavior. It omits error/overwrite semantics, but for a simple setter this is adequate.

  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 and well-structured: action, available worlds in a bulleted list, and return value. Every sentence adds value; no filler or repetition of schema information.

  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 only one parameter, no annotations, and empty schema descriptions, the description fully equips an agent to invoke the tool correctly: what it does, when it applies, what inputs are valid, and what to expect in return. The existence of an output schema further reduces the need to describe return details.

  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 schema provides only a bare 'world' string with zero description coverage. The tool description compensates by giving concrete valid values (earth-313, 'bral') and clarifying the type of worlds accepted. Minor gaps remain around format/case sensitivity, but the semantics are well clarified.

  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 a specific verb and resource: 'Set the current world context for all subsequent queries.' This distinguishes set_world from sibling data-fetching tools (find_accommodations, find_events, etc.) by emphasizing it is a context-setting action rather than a query.

  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 phrase 'for all subsequent queries' clearly indicates when the tool should be used (before other queries). It also enumerates valid world IDs, providing concrete input guidance, though it does not explicitly mention when not to use it or how it relates to describe_world.

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

• find_eventsA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral transparency burden. It explains how 'near' is resolved differently across worlds, that date filtering is primarily for earth-313, and that results are returned as a formatted narrative. These details go beyond the schema and reveal meaningful behavioral traits.

  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 and well-structured: a clear one-line purpose, an organized bullet list of parameters, and a brief return statement. Every sentence adds value 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?

  The description covers all eight optional parameters, highlights world-specific behavior, and notes the output format. Even though an output schema exists, the description provides additional context (e.g., narrative list) and leaves no critical gaps for a tool of this complexity.

  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 description coverage is 0%, and the description compensates fully by explaining every parameter including defaults, formats, and alternatives (e.g., near vs lat/lon, date format, topic examples). This adds substantial meaning beyond the bare schema 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 clearly states 'Find events' with a specific resource (events) and provides a distinct domain separate from sibling tools such as accommodations or gastronomy. It also mentions 'in the current world', which identifies the scope while not requiring inference.

  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 gives clear context on when to use the tool (searching for events) and describes world-specific behavior (near geocoding for earth-313 vs. landmark-resolved for bral). It does not explicitly contrast with sibling tools, but the clear domain and examples imply appropriate usage.

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