Server Quality Checklist

Tool Scores

• libcal_auth_statusA
  4.2/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the burden. It states the tool checks a saved session and provides remediation if expired, but does not disclose the return format, whether any network call is made, or what happens with no saved session. The behavior is generally self-evident for a status check, but richer context would help.

  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 with no filler. The core purpose is stated first, and the actionable recovery command follows immediately. Every word earns its place.

  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 zero-parameter, no-output-schema tool, the description is largely complete: it states what is checked and what to do if the session is expired. A minor gap is not describing what the tool returns, but the purpose sentence implies a validity result, and the recovery step covers the main downstream need.

  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 tool has zero parameters, so parameter semantics are trivially satisfied. The description adds no parameter details, but none are needed. Baseline 4 applies for a no-parameter tool.

  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?

  Description uses a specific verb ('Check whether') and a precise resource ('saved UNC LibCal login session') with an explicit outcome (valid vs expired). The name and description together clearly distinguish this auth-status tool from the sibling booking/availability tools.

  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?

  Clearly indicates when to use the tool: to verify saved session validity. It also gives an actionable alternative by telling the user to run 'npm run login' if expired. It doesn't enumerate when not to use it, but no sibling competes with this auth check, so the guidance is sufficient.

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

• libcal_list_calendarsA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral burden. The verb 'List' clearly indicates a read-only operation with no destructive side effects, and the config.json reference provides useful context about where the result is consumed. It does not spell out authentication requirements, but for a simple listing tool the implied read-only nature is sufficient.

  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, efficient sentence that front-loads the action and resource, then appends the one essential usage hint. There is no filler or redundancy.

  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 zero-parameter, no-output-schema tool, the description fully covers what the tool does and why the agent would call it. It tells the agent the output (calendar names) and how to use it, making it complete enough for correct 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 tool has zero parameters, so parameter semantics are largely not applicable; the baseline for zero parameters is 4. The description adds value by explaining how the output relates to config.json, which is more than the empty schema provides.

  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 states a clear, specific action ('List') and resource ('Apple Calendar calendar names'), which is immediately distinct from the sibling tools that check availability, book, authenticate, or suggest. It also tells the agent the practical outcome, selecting a name for config.json, so the purpose is unambiguous.

  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 parenthetical 'use one in ~/.unc-libcal/config.json as calendarName' implies when the tool is needed (before configuring a calendar) and how its output should be used. However, it does not explicitly state when to use this tool instead of a sibling, nor does it provide exclusions or prerequisites.

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

• libcal_check_availabilityA
  4.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. The verb 'Check' implies a non-destructive read operation, and the date-specific scope is clear. However, it does not explicitly confirm that no booking is made, nor does it mention authentication requirements or output characteristics. These gaps are notable but not severe for an availability-check 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 two compact sentences plus a short category list. The core purpose is front-loaded, the differentiation is in the second sentence, and there is no wasted wording.

  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 tool with 4 documented parameters and a clear purpose, the description is largely complete. The category list and date-scope note cover the key details. The main omission is the response shape (what an 'open slot' looks like), which matters more because there is no output schema, but the operation is simple enough that this is 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?

  Schema coverage is 100%, giving a baseline of 3. The description adds concrete valid category values ('davis-cubes, davis-study-rooms, davis-computers'), which is not in the schema's generic 'Space category id' description. This gives the agent actionable parameter knowledge 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 states a specific verb and resource: 'Check open slots on ONE specific date.' It also explicitly distinguishes itself from the sibling libcal_suggest, which is the cross-day ranked search, so an agent can clearly tell them apart.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use context ('on ONE specific date') and names the alternative for a different case ('For smart ranked search across days, use libcal_suggest instead'). This directly routes the agent to the correct sibling without leaving it to inference.

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

• libcal_suggestA
  4.5/5.0
  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 ranking behavior, same-day priority, numbered option output, and the recommended-option explanation. It does not detail return format or error/no-result behavior, but for a non-destructive suggestion tool the disclosed workflow is reasonably transparent.

  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 front-loaded with the core purpose and then gives a structured, actionable workflow. There is minor redundancy between the opening 'Use BEFORE booking...' and step 1, but the numbered format and categories list keep it scannable and useful.

  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 tool with six optional parameters, no output schema, and no annotations, the description plus detailed input schema covers invocation behavior, defaults, categories, and the follow-up booking step. It does not cover the exact-date+time path to libcal_check_availability or what to do when no options are found, so it is not fully complete.

  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 coverage is 100%, so the baseline is 3. The description adds practical meaning beyond the schema by listing exact category values (davis-cubes, davis-study-rooms, davis-computers), clarifying duration semantics with 'use 180 for max/LibCal limit', and explaining preferred_date/preferred_start_time as ranking boosts.

  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 states a specific action ('Find ranked booking options') on a specific resource with a clear behavioral qualifier ('same-day priority'). It also positions the tool in the booking workflow relative to libcal_book, so an agent can distinguish when this tool is intended.

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

  Usage Guidelines5/5

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

  It explicitly says to use this tool BEFORE booking when the user has not given an exact date+time, provides a required numbered workflow, and names the condition for calling libcal_book instead. It also instructs the agent never to auto-book far-future dates when sooner options exist.

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

• libcal_bookA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It clearly states the user_confirmed=true requirement, the category restrictions, and the anti-far-future-booking guardrail. It could additionally mention side effects like calendar creation or failure behavior, but the key behavioral constraints are well covered.

  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 tightly structured with a numbered workflow and no filler. Each sentence contributes necessary operational guidance, and key constraints are front-loaded before the raw category list.

  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 covers the critical workflow context: prerequisites, confirmation requirement, category options, and when invocation is appropriate. It leaves some operational details to the schema (duration bounds, optional parameters) and doesn't describe error/return behavior, but for a booking action the core invocation context is complete.

  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 coverage is 100%, so the baseline is 3. The description adds value by clarifying that date and start_time come from user choice or libcal_suggest options, that user_confirmed must be true, and by listing valid categories. This goes beyond the schema's basic 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?

  Description clearly states the tool's function: 'Book a specific UNC LibCal slot.' It distinguishes itself from siblings by describing the required prerequisite workflow with libcal_suggest and by limiting scope to confirmed, specific bookings.

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

  Usage Guidelines5/5

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

  Provides explicit, step-by-step usage guidance: call libcal_suggest first for open-ended requests, present options, only call after user picks an option or gives explicit date/time, and never auto-book a far-future date when sooner options exist. This is strong, actionable routing guidance.

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