Skip to main content
Glama

send

Posts a message to another agent in a topic room and wakes the recipient automatically, returning reply IDs for wait_reply; supports multiple recipients and review requests.

Instructions

Post a message for another agent in the TOPIC's room; the recipient is woken automatically. Returns its id (for wait_reply). Several recipients (cross review): the same message to each, one id per recipient (ids); wait_reply(id=ids) waits for all the answers.

Args: to: "claude", "antigravity" (agy) or "codex" (chatgpt); or a list, e.g. ["codex", "antigravity"]. text: self-contained, precise message (context, question, files or commits concerned). topic: short topic (lowercase, digits, -), e.g. "nexuswindows"; one topic per project. info: True = for information only, nobody is woken (closing note, final agreement). due_min: optional deadline in minutes: past it without an answer, track reports "late". files: attachments, absolute paths (images included: the recipient sees them through read); copied into the room when sent. review: review request: the answer must give file:line and severity (or "nothing important"), otherwise it is sent back once to the peer. Omitted: inferred from the text ("review", "relis", "relecture"). A review always goes to BOTH peers (independent opinions): a review sent to one of them is also sent to the other, and the answer lists one id per peer (wait_reply(id=ids)).

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": {
      "to": "<to>",
      "text": "<text>"
    },
    "name": "send"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYes
infoNo
textYes
filesNo
topicNo
reviewNo
due_minNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.8.7
    • addedInput schema / properties / to / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / to / type
      Removed value: -"string"
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "result": {
      -      "title": "Result",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "result"
      -  ],
      -  "title": "sendOutput",
      -  "type": "object"
      -}New value: +null
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: recipient woken automatically, id returned for wait_reply, multi-recipient fan-out returning ids, review requests duplicated to BOTH peers and bounced once if the reply lacks file:line/severity, due_min driving 'late' tracking, and files copied into the room.

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?

Front-loads purpose and return contract before the Args block, and every entry is informative. The review paragraph restates the both-peers rule twice, which is mild redundancy.

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?

With 7 parameters, no output schema and 0% schema coverage, the definition still supplies the return contract (id / ids for wait_reply) and the semantics of every argument, including non-obvious side effects on peers.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry all parameter meaning and does: 'to' lists concrete valid values and list form, 'text' demands self-contained precision, 'topic' gives format and example, 'info', 'due_min', 'files', and 'review' are each explained with behavior, including review inference from the text.

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 resource ('Post a message for another agent in the TOPIC's room') and adds the key behavioral fact that the recipient is woken. It doesn't explicitly contrast with the sibling 'reply', so the send-vs-reply distinction is left implicit.

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?

Gives clear conditions for the optional flags: info=True when nobody should be woken, review for review requests, and that wait_reply(id=ids) is how you wait for the answers. No explicit exclusions naming when to prefer 'reply' or 'inbox' instead.

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