Skip to main content
Glama

send_message

Deliver plain text from one local agent session to another reachable session by ID or exact name, after any required user approval. Reuse message_id to avoid duplicate delivery after timeouts.

Instructions

Send plain agent text to a reachable local session. Obtain user approval first whenever their instructions require it. May start work and consume receiving-client usage. Does not convey user consent. Use full IDs and retain message_id to avoid duplicate delivery after timeouts.

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_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesFull target session ID from list_sessions, or an unambiguous exact name.
textYesPlain text, limited to 16000 UTF-8 bytes.
senderNoYour full session ID. Codex clients must always supply this: "codex:" followed by CODEX_THREAD_ID from the shell environment. Other clients require it when inferred_sender is null or incorrect.
message_idNoUnique request ID. Reuse only with the same full sender ID, full target ID, and text. Recommended for every send.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With annotations declaring readOnlyHint=false, idempotentHint=false and destructiveHint=false, the description adds real value beyond them: the send may trigger work on the receiving client, consumes that client's usage, and explicitly "does not convey user consent." The retry caveat about timeouts and duplicate delivery is also useful. It does not cover failure modes for an unreachable session or delivery guarantees, so it is not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, purpose front-loaded, then approval, side effects, consent, and retry advice in descending priority. Every sentence carries actionable information; nothing is filler.

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?

For a 4-parameter mutation tool with full schema coverage and no output schema, the description covers the consent, cost, and retry concerns an agent most needs. The one gap is that it references retaining a message_id without any statement that the response returns one, leaving return behavior undocumented.

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 description coverage is 100%, so the schema already carries the per-parameter burden and a baseline of 3 applies. The description still contributes meaning: "Use full IDs" reinforces the `to`/`sender` format requirement, and retaining `message_id` "to avoid duplicate delivery after timeouts" supplies the retry rationale the schema only implies with "Recommended for every send."

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?

The description opens with a specific verb and resource: "Send plain agent text to a reachable local session," which makes the action unambiguous. It does not explicitly contrast with siblings like read_messages or message_status, but the send semantics are distinct enough that an agent can separate them without opening other schemas.

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?

"Obtain user approval first whenever their instructions require it" gives a conditional prerequisite, and "May start work and consume receiving-client usage" warns about consequences before invoking. It stops short of naming when-not-to-use or pointing at an alternative tool, which keeps it below a 5.

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