Skip to main content
Glama

List watch events

list_watch_events
Read-onlyIdempotent

List events matched by connection watches, oldest first, using cursor pagination and optional watch_id filtering to retrieve new activity since the last call.

Instructions

Events of this connection's watches (what they matched; list_watches shows the watches themselves), oldest first, kept 14 days. The first call without a cursor returns the oldest kept events. Pass the returned next_cursor on the next call to get only newer events (it is returned even when there are none). Optional watch_id narrows to one watch. Each event: event_id, watch_id, kind, account, message_id, thread_id, received_at; read the message with get_message(account, message_id).

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": "list_watch_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost events returned.
cursorNonext_cursor of the previous call; omit for the oldest kept events.
watch_idNoOnly events of this watch (from create_watch or list_watches).

Output Schema

NameRequiredDescriptionDefault
eventsNo
has_moreNo
next_cursorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / cursor / description
      Added value: +"next_cursor of the previous call; omit for the oldest kept events."
    • addedInput schema / properties / limit / description
      Added value: +"Most events returned."
    • addedInput schema / properties / watch_id / description
      Added value: +"Only events of this watch (from create_watch or list_watches)."
  2. First observedv0.11.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds genuinely new behavior: a 14-day retention window, oldest-first ordering, and the fact that next_cursor is returned even when no new events exist — a detail that prevents needless re-polling confusion.

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-loaded with resource, ordering, and retention, then pagination, then filtering, then the follow-up call. Dense but each sentence carries information; the enumerated event field list is slightly redundant given an output schema exists.

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?

Covers retention, ordering, pagination protocol, filtering, and the natural next call, which is everything an agent needs for a read-only list tool whose output schema already defines the response shape.

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 meaning about cursor semantics (incremental, newer-only) beyond the schema's 'next_cursor of the previous call', and clarifies that watch_id scopes to one watch.

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 resource (watch events) with scope (this connection's watches), ordering (oldest first), and explicitly distinguishes itself from the sibling list_watches, which returns the watches themselves rather than their events.

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?

Gives clear operational guidance: omit the cursor for the oldest kept events, pass next_cursor to get only newer ones, use watch_id to narrow to a single watch, and follow up with get_message(account, message_id) to read the underlying message. It clearly routes away from list_watches, though it does not state any explicit when-not-to-use case.

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