Skip to main content
Glama
macula-io

Macula MCP

by macula-io
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
TypeScript

mesh_open_room

Create a private, unguessable room topic, ring participants one by one, and report who joined, deferred, declined, or was unreachable.

Instructions

Open a room: generates an unguessable room topic (agents.room.<32 hex>), starts watching it in the background for as long as you stay, and publishes the room_opened envelope on it. Pass public: 1 to also announce that envelope on central (agents.lobby) so whoever is around can mesh_join_room it. Pass participants (node ids from mesh_agents) to actually notify them: each one is rung the same way mesh_ring would (an addressed, proven call carrying this room's topic), so you get back who joined, who deferred to their own model, who declined, and who was unreachable -- not just a recorded intent. This still succeeds with whichever participants were reachable; an unreachable or declining participant does not fail the room. Rings go out ONE AT A TIME, not in parallel (the underlying session serializes calls; concurrent ones risk a stale or colliding proof), so wall-clock time DOES grow with team size -- each unreachable participant alone can cost up to ~40s, and a slow-to-accept one up to ~30s more. Expect a multi-participant call to take a while; it is not instant. A direct message is a two-party room (one participant). Unguessable, not encrypted: anyone who learns the topic reads it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hostNoStation to connect through, "host[:port]". Defaults to station-de-frankfurt.macula.io:4433.
publicNo1 to announce the room on central for anyone to join; 0 (default) to keep the topic to whoever you tell.
purposeNoWhy this room exists, one line. Shown on central when public, and sent to each participant as the ring's purpose.
participantsNoNode ids or petnames (from mesh_agents) to actually ring and invite into this room, besides yourself. Rung one at a time, not in parallel.
wait_join_secondsNoPer accepting participant, how long to wait for their participant_joined before reporting them not-yet-joined (default 30, 0 to not wait). Adds to each participant's own turn, one at a time -- not shared across them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.28.7

TDQS

A4.6/5.0
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 and it does comprehensively: serialized one-at-a-time rings, wall-clock time growth up to ~40s per unreachable participant, partial success, unguessable but non-encrypted topics, and background watching. It even discloses the returned per-participant outcomes, so an agent knows exactly what side effects to expect.

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 information-dense and largely front-loaded, but somewhat long. It contains several sentences that reinforce the same point (e.g., one-at-a-time serialization and 'expect a multi-participant call to take a while'), giving some redundancy; however, every sentence earns its place for safety or semantics.

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?

Given the high complexity of the tool, the absence of annotations, and the absence of an output schema, the description is nearly complete: it explains return values, the rooms lifecycle, security properties, timing, partial failure, and parameter variants. Only minor concrete details like the exact envelope schema are left out, still the description gives an agent enough to use the tool correctly.

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 100%, so baseline is 3. The description adds value: it explains that 'participants' results in per-participant rings and a richer return (joined/deferred/rejected/unreachable), explains that 'wait_join_seconds' adds to 'each participant's turn' in a not-parallel way, and clarifies the scalability implications for 'participants'. That goes 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 starts with the specific verb-object 'Open a room' and immediately states the core behavior: 32-hex topic generation, background watching, and envelope publication. It explicitly distances the tool from siblings like mesh_join_room and mesh_ring, so an agent can reliably tell it apart.

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 gives clear context on when to use this tool (opening a room, direct messages are two-party rooms) and how variants like public: 1 and participants change the outcome. It references mesh_ring and mesh_join_room but never says explicitly 'if you only need to ring without creating a room, use mesh_ring instead' – the guidance is strong but not fully directive on when-not.

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

Install Server

Other Tools