hse-mcp

Дедлайны

my_deadlines

Read-onlyIdempotent

Aggregates upcoming and overdue SmartLMS assignments, tests, ELK tasks, windows, requests, and exams into one prioritized deadline list so students can see what needs attention.

Instructions

Что горит: несданные задания и тесты SmartLMS (в том числе просроченные, у которых приём уже закрыт), окна ЕЛК (например, оценка курсов), активные задачи и заявки ЕЛК, ближайшие экзамены/зачёты за days дней вперёд. Элементы без распознанной даты идут в конце с when: null. Возвращает JSON: items — единый список элементов (kind, when, title, course, place, overdue, unread, source, ...), отсортированный: просроченные несданные первыми, затем по времени, затем без даты; sources — статус каждого источника (ok/error/skipped, текст ошибки, warnings). Если источник недоступен (например, ЕЛК не ответил), сводка всё равно возвращается — смотрите sources.

Input Schema

Name	Required	Description	Default
`days`	No	Горизонт в днях вперёд
`courses`	No	Сузить курсы SmartLMS: число — id курса, строка — часть названия. По умолчанию — все видимые курсы: будущие дедлайны берутся у актуальных (не завершённых), просроченные несданные — у любых видимых. Расписание, окна ЕЛК и остальные источники фильтром не ограничиваются.

Output Schema

Name	Required	Description	Default
`items`	Yes
`window`	Yes
`sources`	Yes
`generatedAt`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.1.2Oct 28, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / courses / items / anyOf

Previous value: -[
-  {
-    "exclusiveMinimum": 0,
-    "type": "integer"
-  },
-  {
-    "minLength": 1,
-    "type": "string"
-  }
-]New value: +[
+  {
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "minLength": 1,
+    "type": "string"
+  }
+]

addedOutput schema / properties / items / items / properties / raw / propertyNames
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / sources / propertyNames
```
Added value: +{
+  "type": "string"
+}
```

First observedv0.1.1Oct 25, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, and the description adds real substance on top: partial-failure semantics (the summary is still returned when a source errors, check `sources`), deterministic sort order (overdue unsubmitted first, then by time, then undated), and null-date placement. That is exactly the kind of beyond-annotation context an agent needs for a multi-source aggregator.

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?

Four sentences, front-loaded with what is included before moving to the return shape and the degraded-source caveat. No filler; the ordering of information matches how an agent needs to read it. Output-field naming overlaps slightly with the output schema but the sort rationale is not derivable from it.

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?

Covers the areas that matter for a fan-in aggregator: source coverage, sort semantics, null dates, and graceful degradation with per-source status. Since an output schema exists, restating `items`/`sources` field lists is somewhat redundant, but the explanation of degraded-mode behavior is the piece the schema could not carry.

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% and both parameters are thoroughly documented in the schema, including the courses id-vs-name matching rule and the note that the filter does not apply to schedule/ELK sources. The description only echoes the `days` horizon ('за days дней вперёд') and adds nothing new about parameters, so the baseline 3 applies.

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 precisely enumerates the aggregated resource: unsubmitted SmartLMS assignments/tests (including overdue with closed submission), ELK windows, active ELK tasks/requests, and upcoming exams within a day horizon. This is far more than a restatement of the title 'Дедлайны'. It does not explicitly name the close siblings (my_today, my_week, lms_list_assignments), so differentiation is inferable from scope rather than stated.

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 usage is implied by the enumerated scope and the `days` horizon, which distinguishes it from single-source tools, but the description never says when to prefer this over my_today, my_week, or lms_list_assignments. The only explicit guidance is about handling a failed source ('смотрите sources'), which is about reading output, not about tool choice.

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