Server Quality Checklist

Tool Scores

• find_conflictsC
  2.7/5.0
  Behavior2/5

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

  Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety. However, the description adds no behavioral context beyond the name—it does not specify what the function returns (e.g., list of conflicting events) or behavior with no conflicts.

  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 extremely concise (one sentence), but at the cost of missing essential details. While there is no fluff, the brevity leaves the agent underinformed. A balanced approach would add parameter context without excessive length.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has five parameters, no output schema, and no parameter descriptions, the description is insufficient. It does not specify return format, parameter constraints, or edge cases. The missing information limits the agent's ability to use the tool correctly without additional inference.

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

  Parameters1/5

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

  Schema description coverage is 0%, meaning no parameter descriptions exist in the schema. The description fails to compensate: it does not explain any of the five parameters (start, end, timezone, calendar_id, exclude_event_handle). The agent must guess meanings from parameter names 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 'Find overlapping iCloud events' uses a specific verb and resource, clearly distinguishing the tool from siblings like list_events (which lists all events) and free_busy (which shows availability). It directly conveys the conflict-detection purpose.

  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 guidance on when to use this tool versus alternatives. It does not mention scenarios like 'before creating an event' or contrast with free_busy. The agent must infer usage context from the tool name alone.

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

• get_eventC
  2.7/5.0
  Behavior3/5

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

  Annotations explicitly mark the tool as readOnlyHint: true and destructiveHint: false, so the core safety is well declared. The description adds the unique 'persistent opaque handle' identifier, which is useful. However, it discloses no side effects, response format, or edge cases (e.g., behavior if handle is invalid), so it adds moderate value beyond the annotations.

  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 extremely short (6 words) and front-loaded with the key action. It earns its place but could benefit from a bit more guidance. However, given the simplicity of the tool, brevity is acceptable.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With a single required parameter (0% schema coverage) and no output schema, the description fails to explain how to obtain the handle, return behavior, or error handling. Compared to sibling tools (e.g., list_events, find_conflicts), get_event omits critical context needed for correct invocation.

  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 description coverage is 0%, and the description only mentions 'persistent opaque handle' without explaining the format, origin, or typical sources of this handle. The parameter is required but lacks any usage hints or validation rules, creating a significant gap for an agent to correctly craft the request.

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

  Purpose3/5

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

  The description states the tool retrieves an event by a handle, which is a clear verb+resource pattern. However, it does not distinguish itself from tools like list_events or find_conflicts, leaving ambiguity about when to use this specific method.

  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 alternative event retrieval tools like list_events or find_conflicts. The description does not explain prerequisites (e.g., how to obtain the handle) or contexts where this is preferred.

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

• delete_eventC
  2.9/5.0
  Behavior3/5

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

  Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is clear. The description adds that the deletion uses 'ETag concurrency control,' which is a useful behavioral detail not present in annotations. However, it does not explain how concurrency handling works (e.g., behavior on conflict), what happens to linked resources, or what response to expect. With annotations providing a baseline, the description contributes some but not rich transparency.

  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 a single short sentence, which is concise but comes at the expense of completeness. It earns its place by stating the core action and a key technique, but it omits critical information about parameters and usage. While not verbose, the structure is minimal and does not earn full marks for efficiency given the missing detail.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has 3 parameters (2 required), no output schema, and no parameter descriptions, the description is insufficient. It does not explain how to construct the request_id, what the scope values mean, how the event_handle relates to the ETag, or what happens upon successful deletion (e.g., return type, idempotency guarantees). The annotations provide some context, but the description leaves significant gaps for a destructive operation.

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

  Parameters1/5

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

  Schema description coverage is 0%, so the description bears full responsibility for explaining parameters. It does not clarify the meaning or purpose of any parameter (scope, request_id, event_handle). Even the mention of 'ETag concurrency control' does not directly explain which parameter carries the ETag. The description adds zero semantic value for parameter usage, leaving the agent to guess from parameter names and enum values.

  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 core action ('Delete an event') and adds specificity ('using ETag concurrency control'). The name and description together unambiguously identify the tool's function, and it is well-differentiated from sibling tools like create_event or update_event.

  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 guidance on when to use this tool versus alternatives (e.g., update_event for modifications, or find_conflicts for coordination). There is no mention of prerequisites, such as needing an ETag or event handle, nor any exclusion criteria. The agent must infer usage from the tool name alone.

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

• free_busyB
  3/5.0
  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 description need not restate safety. The phrase 'visible iCloud events' adds context about data source and permissions, but does not explain what 'busy intervals' means in terms of return format (e.g., date ranges, granularity) or behavior when no events are present.

  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 a single sentence with one key piece of information ('visible iCloud events'). It is concise and front-loaded with the verb 'Compute'. However, it could be slightly more informative without adding bulk.

  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 moderate complexity (4 required parameters, no output schema) and poor schema coverage (0%), the description is not complete. It does not explain return values (e.g., busy time slots) or parameter semantics. Annotations provide safety context but do not compensate for missing behavioral and parameter details.

  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 description coverage is 0%, meaning no parameter descriptions exist in the schema. The description provides no parameter details at all—it does not explain what format 'start' and 'end' expect (e.g., ISO 8601), what timezone values are valid, or how calendar_id is used. The schema only shows types and names, so the description should compensate but fails to do so.

  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 uses a specific verb ('Compute') and resource ('busy intervals from visible iCloud events'). It distinguishes itself from siblings like 'list_events' and 'find_conflicts' by focusing on availability rather than event details or conflict detection.

  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 guidance on when to use this tool versus alternatives. Given sibling tools like 'list_events' (which lists events) and 'find_conflicts' (which might find overlapping events), it does not clarify that this tool returns busy intervals for availability checks or when the other tools are more appropriate.

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

• create_eventB
  3.1/5.0
  Behavior3/5

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

  Annotations already declare idempotentHint=true and destructiveHint=false. The description reinforces idempotency but adds no new behavioral details, such as whether the tool validates conflicts, requires specific permissions like 'calendar.write', or what happens to required fields like 'timezone' if omitted. Given the annotation coverage, the description adds minimal extra value.

  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 a single short sentence, which is concise. It front-loads the core action. However, it could be slightly longer to add usage context without losing conciseness.

  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?

  The tool is complex with 13 parameters and many calendar-management siblings, but has no output schema. The description covers creation and idempotency but omits return value expectations (e.g., whether it returns the created event object or just a success indicator), conflict behavior, and calendar visibility scope. An output schema would reduce the need for description completeness, but here its absence creates a 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?

  Schema description coverage is 0%, so the description must compensate. It does not describe any parameters, but the schema itself is detailed with constraints (e.g., rrule max 2000 chars, attendees max 100 items, alarm object structure). With 13 parameters, the description could have clarified key fields like 'request_id' for idempotency or 'calendar_id' for context, but its omission is partially offset by schema richness.

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

  Purpose3/5

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

  The description states 'Create an event idempotently' which identifies the verb and resource. However, it does not clarify what 'idempotently' entails (e.g., whether it means the tool will not create duplicate events if called with the same request_id) and does not distinguish it from sibling tools like 'update_event' or 'find_conflicts'.

  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 guidance on when to use this tool versus alternatives. For example, it does not mention that 'update_event' should be used to modify existing events, or that 'find_conflicts' should be called before creating an event. The agent is left without context for tool selection among 8 siblings.

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

• update_eventB
  3.3/5.0
  Behavior4/5

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

  Annotations already indicate destructiveness and idempotency, but the description adds the ETag concurrency control mechanism, which is a meaningful behavioral detail not present in the annotations. It hints at optimistic concurrency and potential conflicts, enriching the agent's understanding beyond the structured metadata.

  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, concise sentence that is front-loaded with the primary action ('Update an event') and includes a useful detail (ETag concurrency control). Every word contributes value, with no redundancy or filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the complexity of 14 parameters, no output schema, and minimal annotations, the description is insufficient for an agent to invoke the tool correctly. It lacks details on how to obtain the ETag, what the request_id is for, how scope affects updates, or what the response contains. The one-sentence description covers only the surface of the operation.

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

  Parameters1/5

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

  The schema description coverage is 0%, and the description provides no parameter-level information. With 14 parameters, including complex objects like alarms and attendees, the agent receives zero guidance on their meaning or usage. The description's mention of ETag doesn't map to any explicit parameter in the schema, leaving all parameter semantics unexplained.

  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 action ('Update') and the resource ('an event'), making it distinct from sibling tools like create_event or delete_event. The mention of 'ETag concurrency control' adds a specific implementation context, but it doesn't explicitly elaborate on the scope of updates (e.g., single occurrence vs. series) beyond what's implied by the schema.

  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 the tool is for modifying existing events, but it doesn't provide explicit guidance on when to use it versus alternatives like create_event or get_event. It also doesn't mention prerequisites (e.g., obtaining an ETag via get_event) or scenarios where update might be inappropriate. This leaves usage context implied rather than explicit.

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

• list_calendarsA
  3.6/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds no additional behavioral context (e.g., return format, pagination, or authentication), but it does not contradict the annotations. It is minimally adequate.

  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 extremely concise with a single phrase, no wasted words, and front-loaded. It could be slightly more structured (e.g., noting return type), but it is not overly long.

  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's simplicity (no parameters, no output schema), the description is mostly complete. However, it does not describe what the output looks like (e.g., an array of calendar objects) or any caveats, which leaves some ambiguity for an AI agent.

  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?

  There are zero parameters, and schema coverage is 100% trivially. Following the guideline, a baseline of 4 is appropriate since there is nothing to document beyond 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 'List iCloud calendars' clearly states the verb (list) and resource (iCloud calendars), making it unambiguous. It distinguishes the tool from sibling tools like list_events and get_event, which operate on events, not calendars.

  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 the purpose is clear from context, the dimension requires explicit when-to-use or when-not-to-use instructions, which are absent.

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

• list_eventsA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety profile. The description adds context about required range and pagination, but does not disclose additional behaviors like timezone handling, default limit, or response format beyond what annotations provide.

  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-formed phrase with no unnecessary words. It conveys the essential function and distinguishing features efficiently.

  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 six parameters, useful annotations, and no output schema, the description covers the core purpose but lacks details on return values, error conditions, timezone format, and ordering. It is adequate for a straightforward listing but incomplete for handling edge cases or understanding response structure.

  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?

  With 0% schema description coverage, the description partially compensates by indicating that 'explicit range' refers to start/end parameters and 'pagination' to limit/cursor. However, it does not explain calendar_id, timezone, or detailed format of the string parameters, leaving agents to infer from parameter names 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 'List events in an explicit range with pagination' clearly specifies the verb (list), resource (events), and key features (range, pagination). It distinguishes from sibling tools like list_calendars, get_event, and create_event, which have different purposes.

  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 usage when listing events within a specific time range with pagination, but does not explicitly state when to use this tool versus alternatives like get_event (single event) or find_conflicts. No direct when-not or alternative guidance is provided.

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