Skip to main content
Glama

Notifications Tool

notifications

Lists your unread alerts newest first, covering tasks, comments, mentions, summaries and feedback replies, and marks selected items as read after you review them.

Instructions

Lists the person's notifications (the bell), newest first, unread by default: tasks given to them, comments and mentions, the morning summary and answers to their feedback. Use it for "what is new for me?"; for what the whole team is doing use team_activity, for one day's work use my_day. mark_read marks the given ids as read and mark_all_read marks all of them, only when the person has seen them or asks. all: true includes the read ones. Returns each notification's id, type, title, text, time and link, plus the unread count.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "notifications"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNotrue: the latest ones, read or not (default: only unread).
limitNoHow many (default 20).
mark_readNoIds of notifications to mark as read.
mark_all_readNotrue marks every unread notification as read.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

No annotations are present, so the description carries the full burden and mostly delivers: it discloses ordering, default unread filtering, the read-marking side effect with a guardrail against premature marking, and the return shape including the unread count. It omits auth/permission expectations and whether marking is reversible, which are the remaining meaningful gaps for a mixed read/write tool.

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?

Front-loads what the tool does, then alternatives, then mutation rules, then return values – a sensible priority order with no filler. It is dense and slightly overpacked into one paragraph, but sentences are short and each carries 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?

With no output schema, the description compensates by listing returned fields (id, type, title, text, time, link) and the unread count, and it covers the read/write split for a tool with no annotations. Only permission requirements and pagination/limit interplay with the 50-item cap are absent.

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 operational meaning beyond the field docs: 'all: true includes the read ones' is tied to the default-unread framing, and the mark_read/mark_all_read preconditions ('only when the person has seen them or asks') are usage semantics the schema does not state. The limit parameter's behavior and that newest-first ordering is not overridable are left to 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?

States a specific verb and resource ('Lists the person's notifications (the bell)'), names the ordering ('newest first'), the default scope ('unread by default'), and enumerates the notification types covered. An agent knows exactly what this returns without opening the schema.

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 frames the trigger question ('what is new for me?') and routes to the two nearest siblings with their distinct conditions ('for what the whole team is doing use team_activity, for one day's work use my_day'). It also constrains the mutating parameters: mark_read/mark_all_read only 'when the person has seen them or asks'.

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