Skip to main content
Glama
plumbkit

plumb

Official
by plumbkit
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

leave_note

Send a note to another agent by naming a peer session or 'next' agent in this workspace. Start a new thread or reply with a conversation ID; the recipient receives it on next check.

Instructions

Send a message to another agent — a named peer session, or "next" (whoever attaches to this workspace next). Send half of plumb's mailbox; check_messages is the receive half. Full etiquette — addressing, delivery, the exchange cap, cross-project rules: the plumb-chat skill.

Every message belongs to a thread: omit conversation_id to start one (the reply carries its id), or quote an id you were given to reply into that thread (to may then be omitted). A thread is capped at [collab] max_exchanges messages; once spent, replies are refused.

Delivery is by polling only: check_messages or session_start hands it over, exactly once. A peer idle on its human has not seen the message; silence is not refusal, so do not re-send.

Messages are bound to the exact SESSION when it is connected; a disconnected peer, or "next", is delivered by name instead. Cross-project sends need the recipient project's opt-in. Requires [collab] mailbox = true; the body is secret-scrubbed.

Parameters: body (required); to (peer session name or "next" — omitted means "next" on a new thread, the other participant on a reply); conversation_id (reply into an existing thread).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoA peer session name, or "next" for whoever attaches to this workspace next. Omitting it defaults to "next" when you are starting a thread; when you pass a conversation_id it instead resolves to that thread's other participant, and the send is refused if the thread has no other participant or more than one. A name belonging to a session in another workspace is refused up front unless that project has already opted in to cross-project messages.
bodyYesThe message to send (free text).
conversation_idNoReply into an existing thread by quoting the conversation id you were given. Omit to start a new thread.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.17.0
    • changedInput schema / properties / to / description
      Previous value: -"A peer session name, or \"next\" (default) for whoever attaches to this workspace next. A name belonging to a session in another workspace is delivered only if that project allows cross-project messages."New value: +"A peer session name, or \"next\" for whoever attaches to this workspace next. Omitting it defaults to \"next\" when you are starting a thread; when you pass a conversation_id it instead resolves to that thread's other participant, and the send is refused if the thread has no other participant or more than one. A name belonging to a session in another workspace is refused up front unless that project has already opted in to cross-project messages."
  2. First observedv0.16.6

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden. It discloses that delivery is by polling only and happens exactly once, that silence is not refusal, and that messages are bound to the session when connected. It also states the requirement `mailbox = true` and that the body is secret-scrubbed. These are meaningful behavioral details beyond what a schema could 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?

The description is dense but well-organized: purpose first, then addressing, cap, delivery, binding, and prerequisites. Every sentence adds information, and it front-loads the core purpose. It is longer than average, but given the complexity of the tool (addressing, threading, delivery semantics, security), the length is justified. It is not bloated with fluff.

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

Completeness5/5

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

For a tool with three parameters, no output schema, and no annotations, the description covers all essential aspects: how to address, how to start/reply to threads, delivery guarantees, the exchange cap, cross-project rules, and a prerequisite. It even hints at return behavior ('the reply carries its id'). There is nothing an agent needs to know to call it correctly that is missing.

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?

The schema already describes all three parameters at 100% coverage, so the baseline is 3. The description adds extra value by explaining the nuanced behavior of omitting `to` (defaults to 'next' on a new thread, resolves to the other participant on a reply) and by mentioning the thread exchange cap. This goes beyond the schema's parameter docs, so a 4 is warranted.

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+resource: 'Send a message to another agent', and immediately distinguishes it from the sibling `check_messages` ('the receive half'). It clearly states the two addressing modes (`to` as a peer name or `next`), which differentiates it from any other messaging tool. No ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit usage conditions: when to start a thread vs. reply, the cap on exchanges, and the polling-only delivery rule. It names the alternatives (`check_messages` and `session_start`) and tells the agent not to resend when a peer is idle. It also points to the plumb-chat skill for full etiquette and cross-project rules, leaving no doubt about when to use this tool.

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