Skip to main content
Glama

crystal_extension_comms

Send messages and inspect inboxes, outboxes, and audit logs within a crystal's comms boundary. Use it to route agent messages, acknowledge and drain inbox items, or pull mailbox stats.

Instructions

Send messages or inspect inboxes/outboxes/audit logs via the embedded Crystal Comms extension.

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": {
      "action": "<action>"
    },
    "name": "crystal_extension_comms"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoList of recipient IDs (or single '@all', '@channel', 'grp_*') for send
ackNoWhen true, automatically acknowledges and drains listed inbox messages (for list, default: false)
bodyNoMessage body text / payload (for send)
fromNoSender entity ID (required for send; optional outbox filter for list)
inboxNoRecipient entity ID to inspect inbox (for list/clear/ack)
limitNoMaximum messages to return (for list)
actionYesAction: send, list, ack (drain message), clear (drain inbox), or stats (mailbox metrics)
outboxNoSender entity ID to inspect outbox (for list)
channelNoTopic channel (default: 'general')
subjectNoMessage subject line (for send)
reply_toNoOptional causal parent message ID
crystal_idNoTarget crystal ID providing the comms boundary (optional for cave-wide stats)
message_idNoMessage ID to acknowledge and drain from inbox (for ack)
record_dagNoWhen true, records the message as a causal DAG transition node in the crystal (default: false)
json_outputNoReturn JSON array of CommsMessage objects (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations, so the description carries the full burden and it says nothing about behavior: that ack/clear drain (destroy) messages, whether messages are recoverable, how the acks/draining interacts with ack=true, or what stats returns. For a tool with mutating and destructive actions, the description discloses none of this.

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 that names the verbs and the resource efficiently. It is not padded, though its brevity comes at the cost of the missing detail noted elsewhere.

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

Completeness2/5

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

A multiplexed 5-action tool with 15 parameters, no annotations, and no output schema deserves more than one sentence. Nothing explains action selection, which parameters are required per action, or the consequences of the drain/clear operations.

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 parameter meaning is already well covered and the baseline is 3. The description adds no per-action parameter mapping (which of the 15 params apply to send vs list vs ack vs clear), and its 'audit logs' phrasing doesn't map to any parameter or action.

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 specific verbs (send, inspect) and resources (inboxes, outboxes) through the embedded Crystal Comms extension, which distinguishes it from generic siblings like crystal_extension_call/run. However, it advertises 'audit logs' inspection that has no corresponding action in the enum, which blurs the scope slightly.

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

Usage Guidelines2/5

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

No guidance on when to use this versus crystal_extension_call or crystal_extension_run, and no mention of prerequisites such as needing crystal_id for a comms boundary or from/to for send. The agent must infer all conditions from the schema alone.

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