Skip to main content
Glama

get_events

Read-only

Fetches raw live QQ events, including messages, recalls, pokes, joins, requests, and uploads, oldest first. Use a sequence cursor to retrieve only new events and filter by event type.

Instructions

Raw live events received from QQ (messages, recalls, pokes, join/leave, friend/group requests, file uploads, etc.), oldest first. Use since = the last seq you saw to get only new ones.

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": "get_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax events (latest kept)
sinceNoOnly events with seq greater than this
typesNoFilter by post_type or post_type.subtype, e.g. ["message","notice.group_recall","request"]

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered; the description adds the ordering contract ("oldest first") and the cursor semantics of seq, which are genuine behavioral facts. It says nothing about whether events expire, how much history is retained, or what a returned event looks like, so it adds context without fully characterizing the stream.

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?

Two sentences, front-loaded with what the tool returns and its ordering, then a single actionable usage note. Nothing is redundant with the name or padding the text.

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 does the necessary work of telling the agent that raw heterogeneous event records come back in oldest-first order, and it explains the seq cursor needed to use `since` correctly. It leaves the shape of an individual event and how to locate its seq implicit, which is a minor but real gap for a stream-reading tool.

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 coverage is 100%, and the schema already defines limit, since and types with examples, so the baseline is 3. The description reinforces `since` with a practical polling recipe but adds no new detail on limit or the types filter beyond the schema's own post_type.subtype example.

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 uses a clear verb-and-resource framing ("Raw live events received from QQ") and enumerates concrete event categories (messages, recalls, pokes, join/leave, requests, uploads), which makes the payload scope unambiguous. It is distinguishable from the specific sibling getters like get_friend_list or get_file, though it does not explicitly name an alternative event-stream tool.

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?

It gives an explicit operational pattern: "Use since = the last seq you saw to get only new ones," which tells an agent how to poll incrementally rather than re-reading the whole stream. There is no statement of when not to use it or which sibling covers historical/lookup cases, so it stops short of full routing guidance.

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

Deploy Server

Other Tools