Server Quality Checklist

Tool Scores

• calendar_cancelA
  3.8/5.0
  Behavior1/5

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

  The description discloses critical behavioral traits such as irreversibility, notifications to all participants, and the unreliable 200 response. However, it directly contradicts the annotation destructiveHint=false by claiming the operation is 'НЕОБРАТИМО' (irreversible). This contradiction makes the description unreliable, warranting a score of 1.

  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 extensive but well-structured, starting with the most critical warning (irreversibility), then prerequisites, and a detailed breakdown of the occurrence parameter. Every sentence adds essential context, and the use of bold and short paragraphs improves readability without unnecessary fluff. It is appropriately sized for the tool's complexity.

  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?

  Beyond the schema and annotations, this description covers prerequisites, edge cases (recurring meetings), and the tool's post-cancellation verification behavior. An output schema exists, so return values are not needed in the description. However, the unexplained `appointment_id` parameter is a minor gap that prevents a perfect score. Overall, it's nearly complete for the tool's complexity.

  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 description thoroughly explains the `occurrence` parameter: acceptable formats (date, 'tomorrow', exact timestamp), when to omit for one-time meetings, and when it's mandatory for recurring ones. However, the required `appointment_id` parameter is not explained at all, and with 0% schema description coverage, that omission leaves a significant semantic gap. The description only partially compensates for the missing schema details.

  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 'Отменить встречу' (Cancel meeting), identifying the action and resource with specificity. It distinguishes this from sibling tools by emphasizing cancellation and its irreversible nature, leaving no ambiguity about the tool's function.

  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 explicitly states that the tool works only for the organizer and instructs to ask for confirmation with meeting name and time before invocation. It also differentiates between one-time and recurring meetings, explaining when the occurrence parameter is required, providing clear context for correct usage.

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

• calendar_eventA
  4.3/5.0
  Behavior5/5

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

  Beyond the readOnly/idempotent annotations, the description exposes a critical quirk: for recurring meetings, the API returns the series master, not the specific occurrence, and start is the first meeting's date. This is non-obvious, behaviorally relevant context that annotations don't cover.

  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?

  Compact and well-structured: the first sentence enumerates the detail fields, and the second paragraph contains a focused warning about recurring meetings. Every sentence adds value with no repetition or fluff.

  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 one-parameter read-only tool with an output schema, the description covers purpose, parameter source, and the key edge case (recurrence). The agent has sufficient context to invoke the tool correctly without needing return value details.

  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 compensates by stating that appointment_id comes from calendar_schedule(), which is useful. However, it doesn't elaborate on the parameter's format or semantics beyond that source reference; the schema only shows it as a required string.

  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?

  Description clearly states the tool returns meeting details (participants, call link, location, agenda, recurrence). Though it lacks an explicit verb like 'get', the intent is unambiguous and distinguishes from sibling tools like calendar_schedule by referencing its output (appointment_id).

  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?

  Provides explicit guidance on where to obtain appointment_id (from calendar_schedule()). Also gives specific handling for recurring meetings: use calendar_schedule() for the actual occurrence time, which helps the agent decide when to rely on this tool vs alternatives.

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

• calendar_scheduleA
  4.3/5.0
  Behavior5/5

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

  The description goes well beyond the annotations (readOnlyHint, idempotentHint, etc.) by adding crucial behavioral details: date semantics ('Пустые даты = сегодня; date_to включительно'), timezone handling (employee timezone, UTC conversion, office timezones, MYT_TZ override), and the performance implication (one day equals one kairos request, limiting range to 14 days). These context-rich disclosures help the agent understand expected behavior and potential side effects, with no contradiction to 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 moderately long but each sentence serves a purpose: it front-loads the core purpose, then delves into date semantics, timezone handling, and sibling tool pointers. It is well-structured in short paragraphs, though slightly dense. It avoids fluff and repetition, earning a high score, but is not as terse as the top-tier example.

  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 tool has an output schema, so return values are covered elsewhere. The description thoroughly covers usage scope, date interpretation, timezone adjustments, and range limitations, making it quite complete for a read-only calendar query tool. The only notable gap is the undefined 'limit' parameter, which prevents a perfect score. Overall, the description provides sufficient context for safe and correct invocation.

  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 no descriptions (0% coverage), so the description must compensate. It partially does for date parameters by explaining 'date_to включительно' and accepting relative dates like 'завтра'/'послезавтра', and 'Пустые даты = сегодня' clarifies default behavior. However, the 'limit' parameter is never explained, leaving its semantics ambiguous. The description adds meaning for some params but not all, resulting in a baseline-ish score.

  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 identifies the tool as 'Рабочее расписание из MyT' (work schedule from MyT), clearly indicating the resource and source, and explicitly states it is NOT the bank, which distinguishes it from other corporate tools. While there is no explicit verb like 'get' or 'list', the context and subsequent references to calendar_event and calendar_respond imply that this tool provides the schedule list. It effectively differentiates from siblings by pointing to them for further actions.

  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 usage guidance: it mentions 'Дальше: calendar_event(id) — участники, ссылка на созвон, повестка; calendar_respond(id, ...) — ответить' to direct the agent to alternative tools for follow-up actions. It also explains the 14-day range limit and advises to call again with an offset, and provides information about timezone override via MYT_TZ. This is clear when-to-use and when-not-to-use context.

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

• calendar_respondA
  4.6/5.0
  Behavior5/5

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

  The description discloses several behavioral traits beyond the annotations: response overwrites previous ones, is visible to all participants, unclear response values cause errors, and the tool automatically waits/retries on Kairos's 5-second rate limit. These details provide critical operational context that annotations (readOnlyHint=false, destructiveHint=false) do not cover.

  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 moderately sized and front-loaded with the core purpose. It is structured into short paragraphs for purpose, parameter semantics, and rate limits. Each sentence adds value, though it could be slightly more concise without losing nuance.

  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, an output schema exists, and the description covers all essential aspects: usage, parameter meanings, overwrite/visibility behavior, and rate limiting. It provides sufficient context for an agent to select and invoke the tool correctly without needing to consult external documentation.

  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 so effectively by explaining accepted values for 'response' (e.g., 'пойду/да/Accept') and that 'comment' is optional text to the organizer. The 'appointment_id' parameter is not described, but its meaning is self-evident from the name and 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 'Ответить на приглашение' (respond to an invitation) and lists the three possible responses ('пойду'/'не пойду'/'может быть'). This specific verb+resource combination distinguishes it from sibling tools like calendar_cancel or calendar_schedule, making the purpose 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 provides clear usage context: the response is visible to the organizer and participants, and it instructs the agent to show the user the meeting name and chosen response before calling. It also addresses the rate limit by noting that consecutive responses are normal. However, it does not explicitly compare itself to alternative tools like calendar_cancel or calendar_schedule, though that comparison is implied by the distinct purpose.

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

• office_bookingsA
  4.6/5.0
  Behavior4/5

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

  Beyond annotations (readOnlyHint, idempotentHint), the description adds valuable behavioral details: empty date means today, bookings are returned starting from that date (not just that date), and the tool cannot cancel parking. It also clarifies the MyT domain (not bank). This exceeds what annotations alone 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 three short, focused paragraphs: purpose/scope, date behavior, and limitation. Each sentence contributes distinct value with no redundancy or fluff.

  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 simple read-only tool with one optional parameter and an output schema present, the description covers the essentials: what it returns, how the parameter behaves, and a key limitation. The agent has enough to invoke it correctly.

  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 only defines an optional string 'date' with a default, but the description fully explains the semantics: empty date = today, and the tool returns bookings starting from that date, not only for that date. This entirely compensates for the schema's 0% description 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 tool returns office bookings (parking, workspace, lockers) and explicitly says 'Возвращает брони' (returns bookings). It distinguishes itself from sibling tools by scope (office bookings vs. calendar events or parking place availability).

  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 explains the date semantics and one-call sufficiency, and explicitly states it cannot cancel parking bookings, directing users to the MyT app. However, it does not explicitly contrast with sibling tools like parking_book or calendar_cancel, relying on contextual implication.

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

• myt_statusA
  4.7/5.0
  Behavior5/5

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

  Beyond annotations, the description discloses that the tool may re-mint the token and rewrite the session file (while clarifying this is access maintenance, not a user-world change), that it does not print secrets, and that it will report write failures rather than silently returning success. This enriches the readOnlyHint and idempotentHint 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 quite long, with multiple paragraphs covering edge cases and context. While it is front-loaded with the core purpose, the extensive caveats (token renewal, file rewrite, re-login limitation, banking MCP distinction) make it less concise than necessary for a simple status check. All information is relevant, but it could be trimmed.

  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?

  The description covers all essential context: the token self-renewal behavior, the meaning of a zero balance, the internal write side effect, failure reporting, the impossibility of full re-login, and the distinction from a different MCP session. Combined with the output schema and annotations, this provides a complete picture for the 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?

  The tool has zero parameters, so there is nothing to explain. According to the rubric, a 0-parameter tool gets a baseline of 4, and the description adds no parameter-specific information because none is needed.

  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 in the first sentence that this tool checks whether the MyT corporate session is alive by making a request ('Жива ли корпоративная сессия MyT — проверяет ЗАПРОСОМ, а не арифметикой'). It also distinguishes itself from the sibling tool myt_refresh_session by referring to it for forced refresh.

  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 guidance: use this tool to check session status, use myt_refresh_session for forced refresh ('Обновить сессию принудительно — myt_refresh_session()'), and never offer password re-login ('предлагать пользователю передать пароль не надо'). It also clarifies that the banking MCP's refresh_session is unrelated.

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

• parking_bookA
  4.7/5.0
  Behavior5/5

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

  Annotations already mark the tool as not read-only and not destructive, but the description adds substantial behavioral detail: the server returns 200 with an empty body regardless of outcome, so the tool re-reads bookings to print what actually saved, and transliterates car numbers. This is exactly the kind of context that goes beyond structured 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 structured into three short paragraphs, each carrying necessary information: purpose, required parameters, and server behavior. There is no filler; every sentence earns its place and the most important details are 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?

  For a mutation tool with sparse schema descriptions, the description covers required arguments, optional-field defaults, odd server response behavior, post-write verification, and transliteration. Given that an output schema exists, the description does not need to explain return values, and it is unusually complete for this tool type.

  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?

  With 0% schema description coverage, the description compensates by explaining that date and place_id are mandatory and that place_id is sourced from parking_places(). It also explains the defaulting behavior for empty car_number, car_model, and building_id. It does not specify the date format or building_id semantics, but the essential parameter meaning is covered.

  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 opens with the specific verb and resource 'Забронировать место на парковке' (book a parking spot) and immediately clarifies the core effect: it occupies a real place but does not move money. This clearly distinguishes it from sibling read-only tools like parking_places and office_bookings.

  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 explicit usage guidance: date and place_id are required, and place_id must come from parking_places(). It also explains how empty optional fields are filled from the previous booking. It does not explicitly list when-not-to-use scenarios or name alternative tools, but the context and prerequisite make the usage condition clear.

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

• myt_refresh_sessionA
  4.9/5.0
  Behavior5/5

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

  The description discloses important behavioral details beyond annotations: the refresh token is not rotated, repeated calls are safe, and a dead refresh token leads to 'MYT SESSION EXPIRED' requiring a full re-login. The annotations only mark it as not read-only and not destructive, so this adds substantial transparency 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: core action first, then why it's usually unnecessary, the two specific use cases, side-effect transparency, and failure handling. Every sentence contributes meaningful guidance without filler.

  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?

  It fully covers what the tool does, when to use and avoid it, side effects, error behavior, and the next step after expiry. Since an output schema exists, omitting return-value details is acceptable. The description is complete for an agent to invoke and decide correctly.

  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 the schema already covers everything; baseline 4 applies. The description mentions no parameter details, but none are needed here.

  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 action: exchanging a MyT refresh token for a fresh access token, performed forcibly and immediately. It distinguishes itself from siblings like myt_status by focusing on the refresh operation and explicitly referencing the status tool's limitations.

  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 the tool is usually NOT needed and gives exactly two cases when it should be used: checking the refresh token specifically, and refreshing before a long chain of calls. It also provides the alternative full-login command and instructs not to ask the user for a password, giving clear when-to and when-not-to guidance.

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

• parking_placesA
  5/5.0
  Behavior5/5

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

  Beyond the annotations (which already mark it read-only and non-destructive), the description discloses that the tool internally makes 4 requests (settings, buildings, past booking, recommendations), which is a significant performance trait. It also explains the reasoning behind the date behavior and what the response includes (buildings, booking window, default car, spots).

  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 compact 4-sentence paragraph, front-loaded with the core purpose and free of fluff. Every sentence adds value: scope clarification, parameter defaults, internal behavior, and a pointer to the related booking tool. The structure is efficient despite the density.

  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 low parameter complexity and the presence of an output schema, the description covers everything needed: what it does, how parameters behave, what data it returns, and how to proceed to booking. The mention of the 4 internal requests and the parking_book linkage make it contextually complete.

  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 has no descriptions (0% coverage), so the description carries the full burden. It explains both parameters: date defaults to tomorrow and why, and building_id falls back to the last booking or first building. This fully compensates for the schema's lack of detail.

  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 free parking spots at the office for a given date, specifying it's for MyT, not the bank. This distinguishes it from sibling tools like parking_book (booking) and office_bookings. The phrase 'чтобы ответить «где мне парковаться»' reinforces the purpose.

  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 provides explicit guidance on default parameter behavior: empty date means tomorrow because booking opens in advance, and empty building_id uses the last booking's building or the first from the list. It also directs the user to parking_book for the next step, effectively saying 'use this to check availability, use parking_book to book'.

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