Server Quality Checklist

Tool Scores

• get_classroomsA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It explains it returns each classroom's free slots and time, and mentions parameter defaults (e.g., campus_id from environment variable). However, it does not specify the response format (e.g., structure of the output), error handling, or data freshness. For a read-only query tool, the basics are covered but details on return structure are missing.

  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 composed of three sentences, each serving a clear function: the first states the core purpose, the second describes the return data, and the third details the parameters. It is efficient with no filler, though the return description could be more tightly integrated with parameter details. Overall, it is well-structured and front-loaded with the main action.

  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?

  Given the tool has three optional parameters and no output schema, the description adequately covers input parameters and the basic return concept (free slots and time). However, it fails to specify the exact output structure (e.g., whether it returns a list of objects with classroom names and slot arrays), which is critical for an agent to process the result. Error conditions or default behavior for missing environment variables are also not addressed.

  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?

  Although the input schema already provides 100% parameter descriptions, the tool description adds meaningful context beyond the schema: it explains the default behavior of campus_id (from environment variable), enumerates its specific values ('01=西土城，04=沙河'), and gives concrete examples for the building filter ('教1', '主楼'). These additions help an agent understand parameter semantics more deeply than the schema alone.

  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 queries today's free classrooms from BUPT's mobile educational administration. It specifies the exact resource ('今日空教室') and the action ('查询'), making it distinct from siblings like get_campuses which likely returns campus lists. The verb '查询' combined with the resource and scope ('今日') leaves no ambiguity.

  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?

  The description provides no explicit guidance on when to use this tool versus alternatives. While it implies the scope is today's free classrooms, it does not contrast with siblings (e.g., get_schedule for regular schedules, get_today_overview for a broader view). No 'when to use' or 'when not to use' information is given, leaving the agent to infer context solely from tool names.

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

• get_campusesA
  4.2/5.0
  Behavior3/5

  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 discloses the output (campus IDs and main buildings) and its purpose, but does not mention aspects like authentication needs, data freshness, error behavior, or that it is a static list. This is adequate for a simple parameterless tool but lacks depth.

  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 in Chinese that is concise (~25 characters) and front-loaded with the main action. Every phrase adds value: the specific campuses, their IDs, and the use case.

  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 description explains what the tool returns (campuses and main teaching buildings) and why (for campus_id selection). However, it does not specify the return format (e.g., list of objects) or whether buildings are included in the same response. For a simple tool without an output schema, this is mostly complete but has a minor gap.

  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 no parameters, and schema description coverage is 100%. The description implicitly confirms no inputs are needed. Per guidelines, zero parameters receive a baseline score of 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 the tool returns the two campuses (Xitucheng 01, Shahe 04) and their main teaching buildings, with the explicit purpose of selecting campus_id for classroom queries. This distinguishes it from siblings like get_classrooms, which likely returns classrooms for a given campus.

  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 directly states this tool is 'used for selecting campus_id when querying available classrooms,' providing clear context for when to use it. However, it does not explicitly mention when not to use it or cite alternatives among siblings, leaving some implicit guidance.

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

• get_scheduleA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns course name, teacher, classroom, session, and time, and explains the parameter behavior (week vs date, default current week). The verb '查询' implies a read-only operation, and no hidden side effects are suggested. However, it does not mention authorization or error conditions, but for a simple query tool, 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 consists of two concise sentences. It is front-loaded with the purpose, then explains default behavior, parameter usage, and return fields. Every sentence provides necessary information without redundancy or fluff.

  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 low complexity (2 optional params, no output schema, no annotations), the description covers the essential aspects: purpose, parameter behavior, and return fields. It does not mention prerequisites like authentication or data freshness, but these are typical for such a tool. The listing of return fields compensates for the lack of an output schema. Overall, it is sufficiently complete for an agent to select and invoke the tool correctly.

  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 documents both parameters with descriptions including mutual exclusivity and defaults. The tool description adds little beyond reaffirming the schema, providing minimal additional meaning. Baseline 3 is appropriate as the schema does the heavy lifting.

  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 queries the course schedule ('查询北邮移动教务的课程表'), specifying the verb and resource. It differentiates from siblings like get_campuses and get_classrooms, which are about locations, and get_today_overview, which is likely about today's overview. The purpose is unambiguous and specific.

  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 explains default behavior (current week) and how to use week or date parameters to specify a different week. While it does not explicitly exclude cases or contrast with siblings, the context from sibling tool names makes the use case clear. It provides clear context for when to use this tool versus alternatives, though not explicitly.

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

• get_today_overviewA
  4.4/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries full responsibility for behavioral disclosure. It transparently spells out the six specific data items returned and the optional campus_id parameter with default behavior. It does not mention error cases, rate limits, or data freshness guarantees, but for an overview tool with one optional parameter, these omissions are minor.

  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 extremely concise, using a single sentence with a colon-separated list to enumerate the return fields, followed by three example queries. Every word contributes meaning, and the structure front-loads the core functionality before the examples. No unnecessary elaboration.

  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 low parameter count (1, optional), full schema description coverage, and no output schema, the description adequately covers the tool's functionality. It could be more complete by specifying the date range (e.g., always today only) and the format of returned items (e.g., list vs. object), but for an overview tool, the behavioral transparency is strong.

  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 description coverage is 100% (one parameter fully described inline), so baseline is 3. The description adds value by explaining the default value derivation ('默认取环境变量 BUPT_CAMPUS_ID') and listing the campus names ('01=西土城，04=沙河'), which the schema alone does not provide. This goes beyond a simple repeat of 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?

  The description clearly states the tool returns a comprehensive overview including date, week, course list, occupied class periods, free classrooms per period, current free classrooms, and all-day free classrooms. It then lists example queries it can answer, which precisely define the tool's scope and resource. This effectively distinguishes it from siblings like get_classrooms (which likely retrieves classroom information without temporal context) and get_schedule (which probably returns course schedules without classroom availability).

  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 communicates usage by listing the exact question types it answers, such as 'what classes are today' and 'which classrooms are free now'. However, it does not explicitly state when NOT to use this tool or mention alternatives for other scenarios. Given the sibling tools, it would be helpful to clarify, for instance, 'for a full schedule without free room info, use get_schedule'.

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