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

@ola/buzz-mcp

Official
by ola-krutrim
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

buzz_search

Read-onlyIdempotent

Search recent channel and direct messages by sender, time range, channel, and all/channels/DMs; leave the query empty when using filters alone.

Instructions

Search recent messages across your channels and DMs (NIP-50 full text), with Slack-style filters: from (a person — npub / hex / email in wire mode / exact display name, or "me"; resolved fail-closed), after / before (YYYY-MM-DD, an ISO datetime with a zone, epoch seconds, or an age like 24h / 7d), in ("all" default, "channels", or "dms"), channel to scope to one channel, limit (default 20, max 100). query may be empty when a filter is given.

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_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
inNo"all" (default), "channels" or "dms"
fromNoonly messages by this person (npub / hex / email / exact display name / "me")
afterNoonly messages at/after this time (YYYY-MM-DD, ISO datetime with zone, epoch seconds, or 24h / 7d)
limitNo
queryNo
beforeNoonly messages at/before this time (YYYY-MM-DD = through the end of that UTC day)
channelNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.2.36
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / after
      Added value: +{
+  "description": "only messages at/after this time (YYYY-MM-DD, ISO datetime with zone, epoch seconds, or 24h / 7d)",
+  "maxLength": 40,
+  "type": "string"
+}
    • addedInput schema / properties / before
      Added value: +{
+  "description": "only messages at/before this time (YYYY-MM-DD = through the end of that UTC day)",
+  "maxLength": 40,
+  "type": "string"
+}
    • addedInput schema / properties / channel / maxLength
      Added value: +256
    • addedInput schema / properties / from
      Added value: +{
+  "description": "only messages by this person (npub / hex / email / exact display name / \"me\")",
+  "maxLength": 320,
+  "type": "string"
+}
    • addedInput schema / properties / in
      Added value: +{
+  "description": "\"all\" (default), \"channels\" or \"dms\"",
+  "enum": [
+    "all",
+    "channels",
+    "dms"
+  ],
+  "maxLength": 16,
+  "type": "string"
+}
    • addedInput schema / properties / limit / maximum
      Added value: +100
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • addedInput schema / properties / query / maxLength
      Added value: +1000
    • removedInput schema / required
      Removed value: -[
-  "query"
-]
  2. First observedv0.2.6

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description still adds real behavioral value: `from` resolution is fail-closed, default limit is 20 with a hard cap of 100, and `before` with a bare date extends through end of the UTC day. It never states how far back "recent" reaches, which is the one notable omission.

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 the operation and then the filter grammar, with zero filler. The dense backticked parameter listing is the most compact way to convey seven filter semantics.

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?

For a seven-parameter search tool with no output schema, an agent still lacks the return shape, result ordering/ranking, and any pagination story beyond a simple limit. The recency window and the `channel` value format are also unresolved, leaving meaningful gaps for a tool whose results feed further reasoning.

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 only 57%, so the description has to compensate, and it largely does: it documents accepted formats for `from` (npub/hex/email/display name/"me"), the date grammar for `after`/`before`, the default for `in`, and that `query` may be empty when a filter exists. `channel` is left ambiguous — name vs. id vs. channel reference — which keeps it below a 5.

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?

The description opens with a precise verb and resource: search recent messages across channels and DMs using NIP-50 full text. That scope alone separates it from the single-thread readers in the sibling list (buzz_read, buzz_dm_read, buzz_thread_read) without the agent opening any schema.

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?

It explains how to shape a query (filters, empty query allowed when a filter is supplied) but never says when to choose this over buzz_read or buzz_dm_read, nor when not to use it. Usage is implied by the filter mechanics rather than stated as selection 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