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

@ola/buzz-mcp

Official
by ola-krutrim
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

buzz_edit_message

DestructiveIdempotent

Edit one of your own Buzz channel messages by replacing its text (up to 64 KB); clients display the updated content marked as edited. Use dry_run to preview the exact signed event without sending it.

Instructions

Edit one of YOUR OWN messages (kind 40003, h + e tags; new text ≤ 64 KB). Clients show the edited text marked (edited). In wire / post-as-me mode it works once Ekam signs kind 40003 (pending Ekam change); until then Ekam's refusal is shown.

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": {
      "channel": "<channel>",
      "event": "<event>"
    },
    "name": "buzz_edit_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNothe replacement text
eventYesthe target message's <id> (from buzz_read)
channelYeschannel name or id
dry_runNopreview only: resolve everything and show the exact event that would be signed (auth tags redacted) — nothing is signed, uploaded or sent
messageNoalias for `text`

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.36

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint, idempotentHint, and openWorldHint, but the description adds real context on top: the message is replaced in place, clients render it as '(edited)', and in wire/post-as-me mode the call is gated on Ekam signing kind 40003 and currently surfaces Ekam's refusal. That last point is important pre-call expectation setting an agent would not get from structured fields.

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?

Three sentences, purpose front-loaded, and each sentence carries distinct information (scope, client rendering, mode caveat). The wire-format jargon (kind 40003, h + e tags, Ekam) is dense but domain-relevant rather than filler.

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 mutation with a fully described 5-parameter schema and no output schema, the description covers scope, size limit, rendering effect, and the post-as-me gating caveat. It stops short of stating permission requirements or what happens to reactions/threads on the edited message, but nothing needed to invoke it correctly is missing.

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 every parameter including the `message` alias and `dry_run` is already documented in the schema, and the baseline is 3. The description only restates the 64 KB limit already enforced by maxLength and adds no syntax or sourcing detail beyond what the schema provides.

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 specific verb and resource ('Edit one of YOUR OWN messages') and immediately scopes it with ownership, wire kind 40003, and h/e tags. That is enough for an agent to tell this apart from buzz_post, buzz_reply, and buzz_delete without 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?

Usage is implied by the ownership constraint ('YOUR OWN messages'), which effectively tells the agent it cannot edit someone else's message. However, it never names an alternative — not buzz_delete for removal, not buzz_post for reposting — and gives no explicit when-not guidance beyond ownership.

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