Skip to main content
Glama

New notifications

get_new_notifications
Destructive

Check a login for new grades, attendance, messages, announcements, calendar events or homework. The batch is stored and returned again, for the same categories, until acknowledge_notifications.

Instructions

Check a login for new grades, attendance, messages, announcements, calendar events or homework. The batch is stored and returned again, for the same categories, until acknowledge_notifications. Librus reports new calendar events only once, so they need allow_consume_events=true. Changes the grade, attendance and homework views Librus remembers; never opens messages.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "account_alias": "<account_alias>",
      "categories": "<categories>"
    },
    "name": "get_new_notifications"
  }
}

Input Schema

NameRequiredDescriptionDefault
categoriesYesWhich kinds of news to check.
account_aliasYesLogin alias from list_accounts.
allow_consume_eventsNoConsent to fetch read-once calendar news.

Output Schema

NameRequiredDescriptionDefault
dataYes
delivery_semanticsNoat_least_once
acknowledgement_requiredNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.8.1
    • changedOutput schema / $defs / HomeworkItem / properties / marked_done_at / anyOf
      Previous value: -[
      -  {
      -    "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(?:\\.[0-9]{1,6})?(?:Z|[+-][0-9]{2}:[0-9]{2})?$",
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]{1,6})?(Z|[+-][0-9]{2}:[0-9]{2})?$",
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedOutput schema / $defs / MessageTimestamp / properties / local / pattern
      Previous value: -"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(?:\\.[0-9]{1,6})?(?:Z|[+-][0-9]{2}:[0-9]{2})?$"New value: +"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]{1,6})?(Z|[+-][0-9]{2}:[0-9]{2})?$"
    • changedOutput schema / $defs / ModernMessageSummary / properties / read_at / anyOf
      Previous value: -[
      -  {
      -    "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(?:\\.[0-9]{1,6})?(?:Z|[+-][0-9]{2}:[0-9]{2})?$",
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]{1,6})?(Z|[+-][0-9]{2}:[0-9]{2})?$",
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedOutput schema / $defs / ModernMessageSummary / properties / sent_at / pattern
      Previous value: -"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(?:\\.[0-9]{1,6})?(?:Z|[+-][0-9]{2}:[0-9]{2})?$"New value: +"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]{1,6})?(Z|[+-][0-9]{2}:[0-9]{2})?$"
    • changedOutput schema / $defs / Observation / properties / observed_at / pattern
      Previous value: -"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(?:\\.[0-9]{1,6})?(?:Z|[+-][0-9]{2}:[0-9]{2})?$"New value: +"^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\\.[0-9]{1,6})?(Z|[+-][0-9]{2}:[0-9]{2})?$"
  2. Changed1 schema field changedv2.5.0
    • removedOutput schema / additionalProperties
      Removed value: -false
  3. Changed4 schema fields changedv2.3.1
    • addedInput schema / properties / account_alias / description
      Added value: +"Login alias from list_accounts."
    • changedInput schema / properties / account_alias / pattern
      Previous value: -"^(?:[^\\s\\x00-\\x1f\\x7f]|[^\\s\\x00-\\x1f\\x7f](?:[^\\s\\x00-\\x1f\\x7f]| )*[^\\s\\x00-\\x1f\\x7f])$"New value: +"^[^\\s\\x00-\\x1f\\x7f](?: *[^\\s\\x00-\\x1f\\x7f])*$"
    • addedInput schema / properties / allow_consume_events / description
      Added value: +"Consent to fetch read-once calendar news."
    • addedInput schema / properties / categories / description
      Added value: +"Which kinds of news to check."
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With destructiveHint=true and readOnlyHint=false already declared, the description explains exactly why: it changes the grade, attendance and homework views Librus remembers, and it never opens messages. It further discloses that the returned batch is stored and replayed until acknowledgement, and that calendar events are consumed on a single read. These are substantial, non-obvious behavioral facts 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.

Conciseness4/5

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

Four short sentences, front-loaded with what is checked, then the persistence rule, then the consent caveat, then the side effects. Every sentence carries information, though the semicolon-compressed clause about remembered views reads slightly cryptically on first pass.

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 state-mutating, open-world tool with three parameters, the description covers persistence, consent gating, and side-effect scope, and an output schema handles the return shape. It does not say what the result looks like when nothing is new, a minor omission given the available output schema.

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, but the description adds real semantics: categories define the batch identity ('returned again, for the same categories'), and allow_consume_events is framed as required consent for read-once calendar items. account_alias is only indirectly covered via 'a login', which the schema already documents as coming from list_accounts.

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 uses a specific verb ('Check a login') and enumerates the exact resources covered (grades, attendance, messages, announcements, calendar events, homework). It also distinguishes the tool's delta/batch nature from the plain per-category getters that appear as siblings, and names acknowledge_notifications as the reset point.

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?

Usage context is explicit: use it to check for new items, the batch repeats for the same categories until acknowledge_notifications is called, and calendar events require allow_consume_events=true because they are read-once. It lacks an explicit statement of when to prefer the plain category getters (get_grades, get_messages) instead, which would complete the routing guidance.

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