@ola/buzz-mcp

Official

Overview Schema Source Related Servers Discussions Admin

buzz_forward

Forward or quote a message to another channel or person as a link-back reference. Add an optional comment without copying the original text.

Instructions

Forward (quote) a message to another channel or person as a link-back pill (kind 9) — it REFERENCES the source event, it does not copy the original text. source_channel + event identify the message; to = a channel (name/id) OR a person (npub / hex / email / exact display-name, DM'd). Optional comment becomes your note (empty allowed).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source_channel": "<source_channel>",
      "event": "<event>",
      "to": "<to>"
    },
    "name": "buzz_forward"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	target channel (name/id) or person (npub / hex / email / display-name)
`event`	Yes	the message to forward (<id> from buzz_read)
`comment`	No	optional note posted with the pill (empty allowed)
`dry_run`	No	preview only: resolve everything and show the exact event that would be signed (auth tags redacted) — nothing is signed, uploaded or sent
`source_channel`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.2.36Nov 6, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / comment / maxLength
```
Added value: +65536
```

addedInput schema / properties / dry_run

Added value: +{
+  "description": "preview only: resolve everything and show the exact event that would be signed (auth tags redacted) — nothing is signed, uploaded or sent",
+  "type": "boolean"
+}

addedInput schema / properties / event / maxLength
```
Added value: +128
```
addedInput schema / properties / source_channel / maxLength
```
Added value: +256
```

Addedv0.2.7Sep 19, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the write/non-destructive profile is covered. The description usefully adds that the original text is not copied and that a person target is delivered as a DM, but it says nothing about permissions, failure modes when a display-name is ambiguous or unresolvable, or what a successful forward returns.

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?

A single front-loaded sentence plus one compact parameter sentence, with zero filler. It is dense with parentheticals (kind 9, npub/hex/email/display-name) but every fragment carries information an agent needs.

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 and a non-destructive mutation, the definition covers identity of inputs, target resolution, and the reference-vs-copy behavior. The remaining gap is post-call behavior: nothing indicates what is returned (e.g. the new event id or link) or how ambiguous name resolution is reported, which matters for a tool whose target may be a display-name.

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 80%, so most parameters are self-documenting; the one gap is source_channel, which has no schema description and is explained here as one of the two fields that identify the message. It also restates the dual channel/person semantics of 'to' and the 'empty allowed' edge case for comment, adding real meaning beyond the schema.

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 gives a specific verb and resource ('Forward (quote) a message to another channel or person') and then pins down the exact semantics: a link-back pill (kind 9) that REFERENCES the source event rather than copying text. That 'reference not copy' distinction is what separates it from buzz_post/buzz_dm_send, so an agent can pick the right tool without opening a schema.

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 clarifies the two targeting modes ('to' = channel name/id OR a person, in which case it is DM'd) and that the behavior is quoting, not duplicating. It never names an explicit alternative or exclusion (e.g. use buzz_reply for threaded responses, buzz_dm_send for fresh DMs), so routing is inferable rather than stated.

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

Deploy Server