Server Quality Checklist

Tool Scores

• find_flightsA
  3.6/5.0
  Behavior3/5

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

  The description discloses that uppercase country codes silently return no fares and that dates define a departure window returning cheapest fare per route per day. However, it omits other behavioral traits such as rate limits, authentication requirements, or the effect of optional parameters like max_price. With no annotations, the description provides adequate but not comprehensive 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 concise, with a clear front-loaded purpose followed by parameter details in a few sentences. No redundant information is present, and every sentence adds value.

  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 has 6 parameters (3 required), sibling tools, and an output schema, the description sufficiently explains the core function and key parameters. It misses only a brief explanation of max_price, which is a minor gap. The output schema exists but is not described, which is acceptable per rules.

  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 description explains that from_airport and to_airport are IATA codes, destination_country is lowercase ISO2, and dates are ISO format. However, it does not cover max_price at all, and the relationship between to_airport and destination_country is unclear. With 0% schema coverage, the description partly compensates but leaves gaps.

  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 Ryanair one-way fares', identifying the specific airline and fare type. It clearly distinguishes from sibling tools like 'cheapest_per_day' and 'find_anywhere_under' by focusing on one-way fare searching with a departure window.

  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?

  No guidance is provided on when to use this tool versus its siblings (cheapest_per_day, explore_destinations, find_anywhere_under). There is no mention of when to choose this tool over alternatives or any when-not-to-use advice.

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

• find_anywhere_underA
  3.8/5.0
  Behavior3/5

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

  No annotations exist, so the description carries full burden. It explains the core behavior (cheapest fares under a price) but does not specify return format, result count, or limitations (e.g., airline exclusions). It is adequate but not detailed.

  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?

  Two short sentences: first defines the core function, second gives an illustrative use case. No filler or redundancy.

  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?

  For a tool with 4 required params and no schema descriptions, the description leaves out the date parameters. While an output schema exists, the description should explain all inputs. Adequate but incomplete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0%; the description only indirectly explains 'from_airport' and 'max_price' while omitting 'from_date' and 'to_date' entirely. These are required, and their purpose is only hinted at by the example 'this weekend'. Missing explicit parameter 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 it finds cheapest fares from a given airport to any destination under a max price, using a specific verb and resource. It distinguishes from siblings (e.g., 'find_flights' for specific flights) by emphasizing budget flexibility.

  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 ('where can I go for under £50 this weekend') and implies the tool is for open-ended budget searches. However, it does not explicitly state when not to use or compare to siblings.

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

• cheapest_per_dayA
  4/5.0
  Behavior3/5

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

  No annotations are present, so the description must carry the full burden. It explicitly states that days with no flight or price return 'price=None', which is a key behavioral detail. It also specifies the month parameter format. However, it does not disclose potential costs, rate limits, or authentication requirements, leaving some gaps for a tool with no 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?

  The description is three sentences long, with each sentence serving a clear purpose: stating the tool's function, clarifying the month parameter format, and explaining behavior for missing prices. There is no redundant or irrelevant information, making it highly concise and well-structured.

  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 presence of an output schema (not shown but indicated), the description does not need to explain return values. It covers the main use case, the month parameter format, and the behavior for missing data. It could mention potential constraints like maximum date range, but overall it is complete for a simple tool with a limited scope.

  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 0%, so the description must compensate. It adds meaning for the month parameter by specifying the ISO format (YYYY-MM-01). For origin and destination, it only provides an example (DUB->BCN) and mentions 'one route', but does not explicitly state that they should be airport codes or expected format. This is partial compensation.

  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 that the tool provides the cheapest fare per day for one route across a single calendar month, using specific verbs ('cheapest fare per day') and a resource ('one route'). It distinguishes itself from sibling tools (explore_destinations, find_anywhere_under, find_flights) by focusing on a fixed-route monthly calendar view, as evidenced by the example 'what's the cheapest day in July to fly DUB->BCN'.

  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 use case example ('powers ... style prompts'), which implies the intended scenario. However, it does not explicitly mention when not to use the tool or directly compare it to sibling tools. The example is sufficient to guide usage, but lacks explicit exclusions or alternatives.

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

• explore_destinationsA
  4.5/5.0
  Behavior4/5

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

  Discloses no fare lookup, purely network exploration; with no annotations, this adequately conveys behavior for a read-only query.

  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?

  Two concise sentences front-loading purpose and including return format example; 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?

  Output schema exists and description explains return structure; single parameter, no additional context needed.

  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?

  Single parameter 'origin' is clearly implied as the starting airport via backticks; schema coverage is 0% but description adds meaning to the 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?

  Clear verb 'explore' and specific resource 'destinations from origin'; distinguishes from sibling tools by stating 'no fare lookup, just the network'.

  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?

  Explicit examples of when to use: answering reachable countries or if a destination is served. No explicit when-not-to-use, but sibling context implies alternatives for pricing.

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