Server Quality Checklist

Tool Scores

• find_common_free_windowA
  3.6/5.0
  Behavior3/5

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

  Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. Description adds context about finding common free windows but does not discuss rate limits, authorization, or other behavioral traits 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?

  Very concise: two short sentences plus a use case block. Front-loaded with the core purpose. No wasted words.

  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 5 parameters and an output schema, the description covers the main use case but lacks details about return format, parameter defaults, and edge cases. Adequate but not comprehensive.

  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%; the description does not explain individual parameters (year, cantons, language, min_days, school_type). It only briefly mentions 'listed cantons' and 'year', leaving other parameters without semantic context.

  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 date ranges when all listed cantons are simultaneously on holiday, with a concrete use case. It distinguishes from sibling tools like check_date or is_holiday_today.

  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?

  Describes when to use it (planning campaigns, joint events, maintenance). Does not explicitly state when not to use, but context from siblings implies alternatives. Slightly lacking explicit exclusions.

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

• get_public_holidaysA
  3.6/5.0
  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, covering safety and idempotency. The description adds that it returns data for a whole year, but no further behavioral details (e.g., performance, errors) are provided, so the added value is moderate.

  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 short and front-loaded with the purpose, but it contains redundancy (e.g., 'always pass the canton' is stated twice). It could be more concise and structured better.

  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?

  For a simple read-only tool with an output schema, the description covers the main use case but misses the optional language parameter entirely. Given the sibling tools, it does not differentiate explicitly, leaving some context gaps.

  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 low at 33% (only canton has a description). The tool description repeats the need to pass the canton and year but does not explain the format or the optional language parameter, failing to compensate for the missing 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 clearly states the tool returns public holidays for a canton and year, using the verb 'Return' and specifying the resource and scope. It distinguishes itself from siblings like get_school_holidays and is_holiday_today by emphasizing the need to pass a canton for cantonal holidays.

  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 explicitly advises to 'always pass the canton because cantonal holidays differ substantially,' providing clear context on when to use this tool. However, it does not mention when not to use it or list alternative tools for related queries, slightly reducing the score.

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

• check_dateA
  3.7/5.0
  Behavior4/5

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

  Annotations already declare read-only, idempotent, and non-destructive. Description adds context that it checks both school and public holidays, which is beyond annotations.

  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?

  Short but includes redundant use-case block repeating the same idea. Could be more concise without losing meaning.

  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?

  Adequately covers core purpose. Output schema exists, so return values not needed. Distinguishes from siblings partly, but lacks edge-case context.

  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?

  Despite 50% schema coverage, description adds no information about parameters. Relies entirely on schema, which has descriptions for only two of four parameters.

  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 checks a date for school and public holidays. It distinguishes from siblings like is_holiday_today and get_school_holidays.

  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?

  Implies usage for single date checking against both holiday types, but no explicit when-to-use or when-not-to-use compared to alternatives like get_school_holidays.

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

• next_school_holidaysA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds context about computing from today, which is useful but not extensive. No additional behavioral details like rate limits or caching are provided, but the annotations cover the core safety profile.

  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 short, with a clear main sentence and a helpful use case block. No redundant text, though the use case could be integrated more concisely.

  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 description provides the core purpose and context (forward-looking, from today). However, with low parameter documentation and no mention of output format (despite an output schema existing), it is not fully complete for a tool with 4 parameters and sibling alternatives.

  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 only 25% (only 'canton' has a description). The tool description does not mention any parameter details, leaving the other three parameters (count, language, school_type) with no semantic guidance beyond the schema's minimal info.

  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 'Return' and the resource 'next upcoming school holiday periods for a canton', with a specific use case for forward-looking planning. This distinguishes it from sibling tools like 'get_school_holidays' which likely handle date ranges.

  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 use case explains when to use this tool (forward-looking planning without manual date range computation). However, it does not explicitly state when not to use it or provide direct alternatives, leaving some ambiguity.

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

• compare_school_holidaysA
  3.9/5.0
  Behavior3/5

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

  Annotations already provide readOnlyHint, idempotentHint, and openWorldHint. The description adds the output format and default behavior but does not significantly extend behavioral insight 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.

  Conciseness5/5

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

  The description is concise, with a structured use case block. Every sentence adds value, no redundant information.

  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?

  Input schema is covered with defaults and use case. Output schema exists (not shown). The description is adequate for the tool's complexity, though it could elaborate on overlap calculation.

  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%, so the description must compensate. It explains the default for school_type and the purpose, but does not detail the language or cantons format, leaving gaps.

  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 compares school holiday overlap between cantons, returning a pairwise matrix. It is distinct from siblings like get_school_holidays or find_common_free_window.

  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 use case explicitly states when to use the tool (coordinating events across cantonal borders) and explains the default school type (VS) as most relevant. It lacks explicit alternatives, but context is clear.

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

• is_holiday_todayA
  3.9/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering the safe nature. The description adds that it's a convenience wrapper for `check_date`, but does not provide significant additional behavioral context beyond what annotations convey.

  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: two sentences and a tag. Every word earns its place, and the main purpose is front-loaded immediately.

  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 simplicity and the presence of annotations and an output schema, the description adequately covers the main use case. It does not explain return values (not needed due to output schema) and is sufficiently complete for a convenience wrapper.

  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 only 33% (canton described). The description mentions 'given canton' but does not elaborate on `language` or `school_type` parameters. It fails to compensate for the low coverage, leaving agents unclear on optional parameters.

  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 checks if today is a school or public holiday in a given canton, using a specific verb and resource. It distinguishes itself from sibling tool `check_date` as a convenience wrapper for the everyday question.

  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 explicitly says 'one-call convenience for the everyday...are we off today?' and 'convenience wrapper over check_date', providing clear context for when to use this tool over alternatives. However, it does not explicitly state when not to use it.

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

• get_long_weekendsA
  4/5.0
  Behavior4/5

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

  Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds behavioral context: it is computed from federal public holidays from Nager.Date, and cantonal holidays are ignored. This goes beyond annotations.

  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 fairly structured with a main sentence and XML tags, but it contains redundancy (the note about federal holidays appears twice). It could be more concise.

  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 simplicity (one parameter), annotations, and existence of an output schema, the description adequately covers purpose, usage, and behavioral limitations. It is mostly complete, though it does not describe the output 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?

  The input schema has 0% description coverage, but the description implies the 'year' parameter through the use case ('which long weekends exist this year'). However, the description does not explicitly document the parameter or its constraints, so it provides minimal additional meaning.

  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 'Return Swiss long weekends and the bridge days needed to create them', using a specific verb and resource. The use case further clarifies the tool's purpose, distinguishing it from siblings like get_public_holidays.

  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 a use case for planning bridge days and notes the limitation of only considering federal holidays. It implies when to use this tool, but does not explicitly mention alternatives or when not to use it.

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

• list_cantonsA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds that it returns 26 cantons with codes and the CH-XX format, which is helpful but not required.

  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, with the core action in the first sentence and additional guidance in a separate use case section. It is well-structured and front-loaded.

  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?

  For a tool with a single optional parameter and an output schema, the description is mostly adequate but fails to document the language parameter's effect. The use case guidance is helpful, but the parameter gap reduces completeness.

  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 does not mention the 'language' parameter, its default, or how it affects the output. The description only says 'list the 26 Swiss cantons', without clarifying that names vary by language.

  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 it lists the 26 Swiss cantons with ISO codes. It uses a specific verb 'list' and resource 'Swiss cantons', and the use case differentiates from sibling tools which focus on holidays and dates.

  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?

  Explicitly advises to 'call this first' when resolving a canton name to the CH-XX code needed by other tools. Provides clear when-to-use and a concrete use case.

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

• list_school_typesA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=False. The description adds behavioral context: it lists only school types that publish separate holiday tables, and absence means unified table. It also gives example codes for Zurich, enhancing transparency beyond 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 concise with three sentences plus a use_case tag. It is front-loaded with the main action. The use_case tag is helpful but somewhat redundant. No wasted words.

  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 simple listing nature and presence of output schema, the description covers all necessary context: what the tool does, when to use, behavior regarding missing cantons, and example codes. Annotations cover safety. Complete for its purpose.

  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 coverage is 0% and parameters have minimal descriptions ('ISO code', 'Language'). The description does not explain the canton parameter format or language parameter function beyond examples. It mentions canton codes in Zurich example but not the ISO pattern. Description does not compensate for lack of schema coverage.

  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 'List the Schularten (school types) that publish separate holiday tables.' It uses specific verb+resource, and distinguishes from sibling tools like list_cantons and get_school_holidays by focusing on differentiation of holiday tables.

  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 explicit use case: 'Discover whether a canton differentiates school holidays by Schulart before querying.' It also notes that only a minority of cantons differentiate, guiding when to use. However, it does not explicitly state when not to use or suggest alternatives.

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

• source_statusA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate read-only and non-destructive behavior. The description adds that it always returns an evaluable status, which is a behavioral guarantee not covered by annotations. However, it does not detail how reachability or latency is measured.

  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 very concise with two sentences and a structured use_case tag. Every sentence adds value and is front-loaded.

  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 parameters and an output schema, the description fully covers what the tool does, when to use it, and its behavioral guarantee. No gaps are evident.

  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 no parameters, so schema coverage is 100%. Baseline 4 is appropriate; the description does not need to add param information.

  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 reports reachability and latency of upstream sources, with a specific use case for health checks and distinguishing 'no data' from 'source down'. This is distinct from the sibling holiday/date 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?

  The description explicitly mentions when to use the tool: as a health check before queries or to differentiate source status. It does not specify when not to use it, but the use case is well-defined.

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

• export_holidays_icsA
  4.6/5.0
  Behavior5/5

  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. The description adds that the output is a text/calendar document with all-day events, and explains how parameters filter holidays. This complements the annotations without contradiction.

  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: one sentence for the main purpose, a use_case block, and a sentence detailing return and parameters. Every sentence adds value, and there is no redundancy.

  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 output schema exists and annotations are rich, the description covers the essential behavioral and parameter details. It explains the output type and filtering options. Minor omission: it doesn't mention the output is a downloadable file, but this is inferred from 'ready-to-import .ics document.'

  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 schema covers only 20% of parameters with descriptions. The description adds meaning for 'include' (all, public, school) and 'school_type' (VS/MS/BS/EO) beyond patterns. However, 'language' and the constraints on 'year' and 'canton' are not elaborated. Overall, it provides useful context but leaves some gaps.

  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 exports a canton's holidays for a year as an iCalendar document. The use_case block reinforces the purpose, and the sibling tools (e.g., check_date, get_school_holidays) are distinct in that they do not produce ICS files, making this tool's purpose unique and unambiguous.

  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 explicitly says to produce a ready-to-import .ics calendar, implying use when an ICS file is needed. However, it does not explicitly state when not to use it or mention alternatives (e.g., get_school_holidays for JSON). The guidance is clear but lacks exclusionary context.

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

• get_local_holidaysA
  4.6/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds behavioral context: it describes the scope attribute on returned holidays, that municipality accepts name or full subdivision code, and that results list every holiday applying in the locality. No contradictions.

  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 use_case and important_notes sections, but it is somewhat lengthy. Every sentence adds value, but it could be slightly more concise without losing clarity.

  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's complexity (many sibling tools) and the presence of comprehensive annotations and an output schema, the description is complete. It explains the key differentiator (local scope) and adequately covers behavior beyond structured fields.

  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 low (25%), but the description adds meaning for the municipality parameter (accepts name or code) and clarifies the result structure with scope. However, it does not explain the canton, year, or language parameters beyond what the schema already 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 clearly states the tool returns public holidays for a specific municipality or district, including local specifics, and explicitly distinguishes from canton-level tools that flatten away local holidays.

  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 a use case for when to use this tool (to answer locality questions flatted by canton tools) and explains the scope concept (local/regional/national). It does not explicitly list when not to use it or mention sibling alternatives, but the differentiation is clear.

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

• get_school_holidaysA
  4.7/5.0
  Behavior5/5

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

  Beyond annotations (readOnlyHint, idempotentHint), the description discloses duplicate handling and how to collapse them via 'school_type', and explains behavior for cantons that don't differentiate. This adds significant context.

  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 tags but slightly verbose. It could be tightened without losing clarity, but remains efficient.

  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 presence of an output schema, the description adequately covers use case, parameters, and behavioral quirks. It is complete for a tool of moderate complexity.

  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 'Args' section provides clear explanations for all 5 parameters, including format examples and guidance on 'school_type' values. This surpasses the schema descriptions, which had 60% coverage.

  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 'return', resource 'school holiday periods', and constraints (one canton, date range). It distinguishes from siblings like 'get_public_holidays' by focusing on school holidays and canton-specific scope.

  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 'use_case' tag explicitly describes when to use the tool (planning within an explicit from/to window). It does not provide direct exclusions but the sibling list implies alternatives for other holiday types.

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