Server Quality Checklist

Tool Scores

• get_course_historyA
  3.6/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, idempotentHint, and destructiveHint=false, covering safety. The description adds meaningful context beyond annotations by specifying the exact return content (date, item counts, content hash, changelog) and the 'per course' scoping. It does not contradict any annotations and enriches the behavioral picture.

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

  Conciseness3/5

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

  The description is reasonably concise but includes an 'Args' list that duplicates the schema's parameter descriptions. The purpose is front-loaded and clear, but the redundant parameter explanations add length without value. It is not overly verbose but could be tightened. A 3 reflects that it is efficient enough but not exemplary.

  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?

  There is no output schema, so the description carries the burden of explaining the return value, which it does with 'Returns: Timeline of crawl snapshots and detected changes per course.' It also covers the optionality of the course parameter. For a read-only historical tool with clear annotations, it provides sufficient information for correct invocation, though it omits details like pagination or snapshot limits, which are minor given the annotations.

  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 coverage is 100%, so all parameters (subject, grade, course) are fully documented in the input schema. The description reiterates these but does not add new semantics beyond what the schema already provides. The only slight addition is clarifying the optional course behavior, but that is already in the schema's property description. Baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Show the crawl history and change timeline for a specific course.' It specifies the resource (course history) and the verb (show), and distinguishes it from typical curriculum-content tools by focusing on crawl snapshots and changelogs. It is clear but does not explicitly name sibling tools, so it gets a 4 rather than a 5.

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

  Usage Guidelines3/5

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

  The description implies when to use it (when needing historical crawl data), and provides the conditional behavior for the 'course' parameter (if omitted, shows all courses). However, it does not compare with alternatives like get_curriculum_changes or list_courses, nor does it state when not to use it. This is adequate but leaves some selection judgment to the agent.

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

• search_curriculumA
  3.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds value by detailing the return structure (source type, course, subject, grade metadata) and mentioning the limit default/max, exceeding what annotations alone provide. No contradictions found.

  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 well-structured with a clear purpose sentence, an Args block listing parameters concisely, and a Returns section. It front-loads the main action and includes no fluff. The Args block mirrors the schema, but it's compact and aids readability.

  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?

  There is no output schema, so the description adequately covers return values by describing the metadata fields. All parameters are documented with defaults and constraints in both schema and description. Missing details like pagination or error handling are not critical for a search tool, so completeness is good.

  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 coverage is 100% with detailed descriptions for each parameter, so the baseline is 3. The description's Args block repeats schema information but adds examples for query (e.g., 'empathetic design thinking') and subject (e.g., 'adst'), offering slightly more pragmatic guidance without substantially expanding semantics.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool searches BC curriculum (K-12) for specific content types and returns structured results with metadata. It identifies the resource and action, but does not explicitly contrast with sibling tools like search_cross_curricular, so it's clear but not fully differentiated.

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

  Usage Guidelines3/5

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

  The description implies it is the general full-text search tool for curriculum content, but it does not state when to use this tool over alternatives like search_cross_curricular or get_course_curriculum. No when-not guidance or explicit alternatives are provided, leaving some inference to the agent.

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

• get_grade_progressionA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral detail beyond annotations: the focus default ('all'), the query-filtering behavior, and what the return contains. With annotations carrying the safety burden, a 3 is fair — it adds context but not deep behavioral disclosure like ordering or edge cases.

  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 well structured with a front-loaded purpose, a clear Args section, and a Returns line. There is minor redundancy — the query-filtering behavior is described twice (once in the intro, once in the Args) — but the organization makes it easy to scan, and no sentence is wasted.

  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?

  For a 4-parameter tool with an empty schema and no output schema, the description is remarkably complete: it covers every parameter with defaults and enums, and states the return shape (grade-by-grade breakdown, optionally filtered). Minor gaps include unspecified grade ordering (K→12 vs 12→K) and error behavior, but nothing an agent critically needs to call it correctly 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?

  The input schema is empty (0 parameters), so the description carries the full burden — and it does so excellently. The Args block documents all four parameters with types, ranges, default values, and enum options ('big_ideas', 'competencies', 'content', 'all'), plus the behavior of the query filter with a concrete example. This fully compensates for the empty schema and exceeds the baseline-4 expectation for a 0-param schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb+resource ('Show how Big Ideas, Competencies, and Content progress across grade levels for a BC subject'), which is clear and unambiguous. It distinguishes itself from siblings by its grade-progression angle, though it never names any sibling directly. The core purpose is evident and not a tautology.

  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 for when to use it ('Useful for understanding scaffolding, prerequisites, and learning trajectories'), and explains the query-filtering behavior that makes it preferable over a full dump. However, it does not explicitly name alternatives or state when not to use it versus siblings like get_course_curriculum or get_competency_connections.

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

• get_competency_connectionsA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds useful behavioral details: it returns 'related competencies from other courses/subjects with similarity ranking' and describes the scope parameter's effect. No contradiction with annotations, so a 4 is appropriate.

  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: it leads with the core purpose, adds a brief usage context, then lists arguments and the return. No filler or redundant sentences, and the format is easy to parse.

  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 two-parameter read-only tool with a fully documented schema and no output schema, the description covers purpose, parameters, default scope, and return format. Nothing an agent needs to invoke it correctly 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%, and the description reproduces the schema's parameter descriptions verbatim for both competency_text and scope. It adds no new meaning beyond the schema, so the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool 'find[s] curricular competencies that appear across multiple subjects or courses,' which is a specific action with a clear resource. However, it does not explicitly distinguish itself from similar sibling tools like search_cross_curricular, so it misses the differentiator that would earn a 5.

  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 context for when to use: 'useful for interdisciplinary curriculum design and identifying transferable skills.' It does not mention alternatives or when not to use, but the use case is well defined, so it meets the 'clear context, no exclusions' level.

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

• get_course_curriculumA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by specifying the output structure ('full three-column structure'), grouping by domain, and including elaborations. It also clarifies the behavior when 'course' is omitted (returns all courses), which is beyond the schema.

  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 appropriately brief and front-loaded with the core purpose. The Arg/Returns section repeats schema details but adds the omission behavior and example slugs. No extraneous text; it is efficient without being terse.

  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 lack of an output schema, the description sufficiently explains what the tool returns (three-column structure, components, elaborations). It also covers the optional parameter behavior, making it complete for a read-only retrieval tool. Missing any explicit mention of error cases, but those are not critical for this context.

  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%, so all parameters are already documented. The description adds meaningful semantic detail by explaining the effect of omitting the optional 'course' parameter and providing example slugs, which helps the agent form valid values even though the schema already covers the enum for subject.

  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 a specific verb ('Get') and resource ('complete BC curriculum for a specific course'), then enumerates the exact components (Big Ideas, Curricular Competencies, Content/KDU items). This distinguishes it from siblings like search_curriculum and list_courses by focusing on the full structured curriculum rather than search results or course listings.

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

  Usage Guidelines3/5

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

  It is implied that this tool is for retrieving the full curriculum for a given course, but there is no explicit guidance on when to prefer it over alternatives such as get_grade_progression or get_competency_connections. The description does not mention exclusion criteria or alternative use cases, leaving an agent to infer the appropriate context from the sibling names.

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

• get_curriculum_changesA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds behavioral context beyond that: the requirement of at least two crawls and the return structure (course-level summary plus item-level detail). This is valuable and non-redundant, though it leaves out performance or error details.

  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 well-structured: a clear purpose sentence, an Args list, and a Returns note. It is not overly verbose, but the Args section duplicates schema content, adding slight redundancy. This keeps it from a 5, but it remains efficient and scannable.

  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 five optional parameters and no output schema, the description explains the return type (course-level and item-level detail) and the prerequisite for meaningful results. It lacks explicit examples or edge-condition guidance, but for a read-only query tool with good schema coverage, it is sufficiently complete for an agent to call 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 all five parameters with types, defaults, and examples. The description's Args section restates the same info without adding new meaning (e.g., it repeats defaults and the since pattern). At best it reinforces, but it does not compensate for any gap, so a baseline 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 verb 'Show' and the resource 'what changed in BC curriculum since a given date', and explains it detects added, removed, and modified Big Ideas, Competencies, and Content items. This distinguishes it from sibling tools like get_course_history, which would imply course-specific historical detail, whereas this tool focuses on cross-crawl changes.

  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 context for usage: it is for showing curriculum changes over time, with a date filter. It also notes a prerequisite ('Requires at least two crawls to have change data'). However, it does not explicitly name alternatives or state when NOT to use it, so it stops short of a 5.

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

• search_cross_curricularA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is established. The description adds the return format: 'Groups of curriculum items connected by shared language across subjects,' which is useful. It does not elaborate on pagination, error behavior, or edge cases, but for a read-only search tool, the combination of annotations and return description provides sufficient transparency.

  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 well-structured: a purpose statement, a list of parameters with examples, and a return note. It is efficient and front-loaded, with the core purpose stated first. While the parameter list adds length, it is justified given the five parameters and the benefit of examples. There is minimal filler.

  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?

  For a search tool with five parameters, two required, and no output schema, the description adequately covers purpose, parameters, and return type. The main missing element is explicit usage guidance relative to siblings, but that gap is already scored under usage guidelines. Given the annotations and schema richness, the description is overall complete for practical invocation.

  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 documents all parameters with descriptions and defaults (100% coverage). The description goes further by providing concrete examples (e.g., subject slugs, focus values, query terms) and clarifying how parameters interact, such as 'query' narrowing results. This adds meaning beyond the schema and helps an agent construct valid calls.

  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: finding curriculum elements shared between two or more subjects at the same grade level. It specifies the resource (curriculum elements), the verb (find/identifies), and the specific types (competencies, big ideas, content). The phrase 'cross-curricular' and reference to interdisciplinary planning distinguish it from single-subject search siblings like search_curriculum.

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

  Usage Guidelines3/5

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

  The description mentions it is 'essential for interdisciplinary planning,' which implies a use case, but it does not explicitly contrast with sibling tools such as search_curriculum or get_competency_connections. No conditions or exclusions are given, leaving an agent to infer when this is the appropriate choice versus alternatives. Some guidance on when not to use it would improve clarity.

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

• list_coursesA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, so safety is covered. The description adds value by specifying the return structure ('List of courses with subject, grade, name, and URL'), which goes beyond the annotations. It does not mention pagination or error behaviors, but these are minor given the read-only idempotent nature.

  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 concise and well-organized: a one-line purpose, then an Args block, then Returns. The main purpose is front-loaded. It repeats some schema information, but this is acceptable for quick scanning. There is no fluff, so it earns a strong score.

  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 is a simple list operation with only two optional parameters and no output schema, the description provides everything needed: the discovery use-case, filter options, and return fields. Combined with annotations covering the safety profile, an agent can confidently invoke this tool without ambiguity.

  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% and both parameters have clear descriptions in the schema (e.g., grade '0=Kindergarten, 1-12' and subject with an enum of valid slugs). The description's Args section restates these without adding new meaning, so it does not enhance beyond the schema. Hence the baseline of 3 applies.

  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 verb 'List' and the resource 'all available courses in the BC curriculum database (K-12)', immediately distinguishing it from siblings like 'get_course_curriculum' and 'search_curriculum'. It also frames the tool's role as a discovery step before querying specific curriculum data, which is unique among the siblings.

  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 to discover what courses are available before querying specific curriculum data', giving a clear when-to-use scenario. However, it does not name any alternative tool or state when not to use it, so it falls short of the full 5 which requires explicit alternatives or exclusions.

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