Skip to main content
Glama
Sign In
@ola/buzz-mcp

@ola/buzz-mcp

Official
by ola-krutrim
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

buzz_mark_read

Idempotent

Marks a channel or DM as read up to the newest or a specific message, or marks all conversations read, so Buzz read state stays synced across clients.

Instructions

Mark a channel or DM read (like Slack's mark-as-read) — NIP-RS read state (kind 30078), NIP-44 encrypted to you so the relay can't read it, synced with other Buzz clients. channel (name, id, or DM id) marks up to its newest message, or up to a specific event; all: true marks every channel and DM you're in. Only moves forward (never marks unread). Agent mode only — refused in wire / post-as-me mode.

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": "buzz_mark_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNomark every channel and DM you're in
eventNomark read up to this message <id> (default: the newest)
channelNochannel name / id, or a DM's channel id
dry_runNopreview only: resolve everything and show the exact event that would be signed (auth tags redacted) — nothing is signed, uploaded or sent

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.36

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing that state is NIP-44 encrypted to the caller (relay cannot read it), synced across Buzz clients, monotonic ("Only moves forward (never marks unread)"), and gated on agent mode. These are non-obvious behavioral facts, especially the mode restriction, that the annotations (readOnlyHint false, idempotentHint true) do not convey.

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?

Purpose is front-loaded in the first clause, followed by mechanism, parameter behavior, and constraints, with zero filler. The single dense paragraph packs several distinct ideas (crypto, sync, monotonicity, mode gate), which slightly hurts scanability but not economy.

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 write-state tool with no output schema and no annotations covering the mode restriction, the description supplies the critical context: encryption, forward-only semantics, dry_run preview meaning, and the agent-mode gate. The main remaining gap is that every parameter is optional and the description never says what happens if none is supplied.

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?

With 100% schema coverage the baseline is 3, but the description adds cross-parameter meaning the schema lacks: `channel` accepts a name, id, or DM channel id and marks up to its newest message, and `event` overrides that ceiling. It does not state whether at least one of `all`/`channel` is required, leaving ambiguity when all optional params are omitted.

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 concrete verb and resource ("Mark a channel or DM read") and anchors it with an analogy ("like Slack's mark-as-read"), then names the underlying mechanism (NIP-RS read state, kind 30078). An agent can immediately distinguish this from buzz_read, buzz_unread, and buzz_dm_read.

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?

Explains the three selection paths clearly: `channel` scopes to one channel/DM, `event` scopes to a specific message, `all: true` covers everything. It also states a real exclusion ("Agent mode only — refused in wire / post-as-me mode"), which prevents a failed call. It does not explicitly name a sibling for the unread/counterpart case, so it falls just short of full when/when-not/alternatives 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