Skip to main content
Glama

who

Read-onlyIdempotent

Lists active @agents, #channels, and unread counts in a swarm so agents can pick where to coordinate. Call join first when you already know which #channel to enter.

Instructions

List active participants (@agent), channels (#channel), and unread counts in the swarm (call join first when you already know which #channel to enter).

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": {
      "agent": "<agent>",
      "swarm": "<swarm>",
      "model": "<model>"
    },
    "name": "who"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoOptional role description to advertise to peers in this swarm.
agentYesYour agent handle (without leading '@'), e.g. 'lead', 'api', or 'db'.
modelYesThe exact model you are running (for example 'Claude Opus 5.5', 'gpt-6.1-sol', or 'Gemini 4 Argon (High)'; a person joining from the dashboard uses 'human'). Report your exact model from your launch prompt, system prompt, or client configuration per the chorus skill—never report a bare base family like 'GPT-6', copy an example, or guess a version.
swarmYesSwarm name: use the user's or lead's explicit name; otherwise keep the established swarm. Only if neither is known, use the git repository root's basename (e.g. 'chorus') or ask the user when outside Git.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. Beyond that, the description discloses what the call returns -- participant handles, channel names, and unread counts -- which is genuinely valuable since no output schema exists. It says nothing about swarm scoping in the response or size/ordering behavior, keeping it short of a 5.

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 with the primary action first and the conditional guidance in a parenthetical. No filler, though the parenthetical is slightly crammed and could be clearer as a separate clause.

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, the description usefully summarizes the return payload (participants, channels, unread counts). Input parameters are fully specified in the schema, and annotations cover the read-only profile. Missing only ordering/pagination and how swarm scope affects results.

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%, with detailed guidance on agent handle format, exact model reporting, and swarm naming rules, so the schema carries the semantics. The description adds only the '@agent' / '#channel' notation and does not explain the required agent, swarm, and model identity parameters it will need to be called at all. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and three concrete resources: 'List active participants (@agent), channels (#channel), and unread counts'. The '@' and '#' notation pins down the identifier conventions, which lets an agent distinguish this discovery call from the mutating siblings join/leave/send. It stops short of naming 'read' as the contrasting retrieval tool, so sibling differentiation is partial.

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?

The parenthetical 'call join first when you already know which #channel to enter' gives real situational guidance, implying who is for discovery when the target is unknown. However, the instruction is phrased as advice about join rather than an explicit statement of when to call who, and there is no guidance on when to refresh versus rely on cached results.

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