Server Quality Checklist

Tool Scores

• calendar_free_slotsA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description must fully disclose behavioral traits. It covers busy sources (selected calendars), ignored event types, and defaults. However, it does not describe the output format (e.g., list of time slots), edge cases (if no free slots), or rate limits. The description is somewhat transparent but lacks completeness on return structure.

  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 two sentences, front-loaded with purpose and example. Every sentence adds value: the first gives the core function and use case, the second explains default behavior and date format. No fluff 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?

  Given 8 parameters (1 required), no output schema, and no annotations, the description is fairly complete: it explains date range, daily windows, calendar selection, and handling of all-day/free events. However, it omits the output format (what does a free slot look like?) and any pagination or limit details. This is a moderate gap.

  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 baseline is 3. The description adds context on default behavior (e.g., all-day events ignored) but the parameter descriptions in the schema are already detailed. No significant additional meaning beyond schema is provided.

  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 finds free time slots across calendars in a date range, with an example use case ('plan a call or a week'). The verb 'finds' and resource 'free time slots' are specific. It implicitly differentiates from siblings (calendar_calendars, calendar_events) by focusing on availability, not listing calendars or events.

  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 explains default behaviors (ignoring all-day/free events) and recommends date format, but does not explicitly state when to use this tool versus calendar_events or calendar_calendars. No alternatives or exclusions are mentioned. Usage context is implied but not comparative.

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

• calendar_eventsA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the full behavioral burden. It discloses the supported actions, date format recommendations, read defaults, and the attendee limitation. However, it lacks information on error handling, permission requirements, or behavior for write operations beyond stating defaults. This is adequate but leaves gaps for a 19-parameter 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 four sentences, each adding value: purpose, format recommendation, reading default, and a critical limitation. It is front-loaded with the main action and avoids redundancy. No fluff or unnecessary details.

  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?

  Despite the tool's complexity (19 parameters, multiple actions, recurring events, alarms), the description is brief and does not cover key aspects like how to handle recurring events (span, occurrenceStart), error scenarios, or permission needs. The attendee limitation is the only non-obvious detail. For a tool of this complexity, the description is incomplete.

  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 description's baseline is 3. It adds value by recommending date format, explaining read defaults, and clarifying endDate behavior for all-day events. However, for most parameters (e.g., span, recurrenceRules, alarms), the description provides no additional semantics beyond the schema descriptions.

  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 begins with 'Manages Apple Calendar events: read, create, update, delete,' explicitly stating the verb (manages) and resource (events) with all supported actions. It distinguishes from sibling tools calendar_calendars and calendar_free_slots, which manage calendars and find free slots respectively, by focusing on event operations.

  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 practical usage guidance, including recommended date format ('YYYY-MM-DD HH:mm:ss') and default reading window ('today + 14 days'). It also notes a key limitation ('Attendee participation cannot be changed') that prevents misuse. However, it does not explicitly compare with sibling tools or state when not to use this tool.

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

• calendar_calendarsA
  4.3/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Notes that read-only operation and disambiguates issues with duplicate calendar names. Does not mention rate limits or auth, but adequate for simple 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?

  Two concise sentences that deliver purpose, usage guidance, and a caveat without waste. Each sentence adds value.

  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 no output schema, description explains returned fields. Provides workflow suggestion with sibling tools. Sufficient for a simple read operation.

  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% for one parameter (action). Description adds no additional meaning beyond the schema's enum and optionality. 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?

  Clearly states verb 'Reads' and resource 'calendar collections', lists returned fields (name, account, id, writable), and distinguishes from sibling tools by indicating it's the first step for discovery.

  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?

  Explicitly instructs to use this first to discover exact calendar names before filtering or creating events, providing workflow context. Does not explicitly state when not to use, but the guidance is strong.

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