Skip to main content
Glama

get_unread

Read-only

Retrieves new unseen QQ messages grouped by chat and marks them as seen, with optional message limits, chat targeting, and seen-status control.

Instructions

New incoming messages you have not seen yet (since the server started or your last get_unread/read_chat), grouped by chat. Marks them as seen.

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_unread"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax messages
targetNoOnly this chat (same forms as other tools)
mark_seenNoMark returned messages as seen

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

The description discloses real state behavior beyond the annotations — that results are grouped by chat and that messages are marked seen as a side effect, with the cursor reset by this or read_chat. But that disclosure directly conflicts with the supplied readOnlyHint=true and destructiveHint=false, since marking messages as seen mutates server state. The description is arguably the more accurate party, yet the contradiction leaves an agent unsure whether the call has side effects.

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?

Two sentences, front-loaded with the resource and the grouping behavior, with the cursor definition in a tight parenthetical. Nothing is wasted, though the final clause about marking as seen deserves more prominence given it is the tool's only mutating behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description is the only place the return shape is described — 'grouped by chat' is helpful but thin for a tool whose main value is the grouping structure. Combined with the unresolved side-effect question and the ambiguous limit scope, it is adequate but leaves meaningful gaps for a polling 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 description coverage is 100%, so limit, target, and mark_seen are already documented; baseline is 3. The description adds some meaning by tying 'seen' state to the tool's cursor semantics, but it does not clarify whether limit applies per chat or overall, nor what 'same forms as other tools' means for target.

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 names a specific resource and scope: 'new incoming messages you have not seen yet', grouped by chat. It also defines what 'unseen' means (since server start or last get_unread/read_chat), which lets an agent distinguish this from a history-reading sibling like read_chat. It falls short of 5 because it does not explicitly contrast itself with the obvious alternative for reading a full conversation.

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?

Usage is implied rather than stated: an agent can infer this is the 'what's new' poll, and the mention that get_unread/read_chat reset the cursor is a useful usage hint. However, there is no explicit 'use this when / use read_chat when' routing guidance and no warning about how polling interacts with the default mark_seen=true.

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