Skip to main content
Glama
Sign In
throng

throng

by agent-runbooks
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

send_message

Destructive

Sends a follow-up message to an existing throng session, optionally steering or running in the background, and returns the agent result or a queued state.

Instructions

Sends the next message into an earlier session (session_id from run_thronglet) and returns the same JSON as run_thronglet. A message to a session whose turn is still running waits for that turn to end: turns on one session never overlap. With background: true the call returns {session_id, state, queued} as soon as the turn runs; collect the result with wait_thronglet. steer: true interrupts the running turn and delivers this message next; queued messages follow it. A session its harness cannot continue (resume or load) takes no further message, steer included: list_thronglets shows it as accepts_messages: false.

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": {
      "session_id": "<session_id>",
      "prompt": "<prompt>"
    },
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
steerNoInterrupt the running turn (session/cancel) and run this message as the very next turn, ahead of queued messages. The in-flight tool call is aborted; a half-applied edit may remain.
promptYesNext message for the agent
schemaNoJSON Schema (draft-07 or 2020-12) for structured output: the agent ends with a matching JSON value as its final message, returned as `structured` instead of `text`
timeout_sNoWall-clock limit for the run in seconds; default from config (21600)
backgroundNoReturn as soon as the turn is running (or queued behind the session's current turn); collect the result with wait_thronglet
session_idYessession_id from run_thronglet

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.4
    • changedInput schema / properties / schema / description
      Previous value: -"JSON Schema (draft-07 or 2020-12) for structured output: the agent submits a matching result, returned as `structured` instead of `text`"New value: +"JSON Schema (draft-07 or 2020-12) for structured output: the agent ends with a matching JSON value as its final message, returned as `structured` instead of `text`"
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnly false, destructive true, non-idempotent), it explains serialized turns, queuing, early return under background, steer interruption, and that queued messages follow a steer. It also discloses that sessions whose harness cannot resume or load reject all messages, which prevents futile calls.

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?

The description is front-loaded with the operation and then moves through waiting, background, steer, and invalid-session behavior. Each sentence carries operational information, and despite a few long clauses there is no filler or restatement of schema-only fields.

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?

For a six-parameter, concurrency-sensitive tool with no output schema, it explains the normal return (same JSON as run_thronglet), the background return shape, how to collect it, and the blocked-session case. Remaining details such as timeout_s and the structured-output schema are fully covered in the input schema, so nothing needed to call it correctly is missing.

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 descriptions already cover all six parameters at 100%, so the baseline is 3. The description still adds useful semantics: session_id is sourced from run_thronglet, background returns {session_id, state, queued} and should be paired with wait_thronglet, and a steer precedes queued messages. It does not add meaning for prompt, schema, or timeout_s, so it is not a 5.

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 first sentence states a concrete verb and resource: it sends the next message into an earlier session identified by session_id from run_thronglet, and returns the same JSON. That distinguishes it from run_thronglet and wait_thronglet, so an agent can select it without opening the schema.

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 conditions for background, steer, and sessions that cannot be continued, and it points to wait_thronglet for background results and list_thronglets for accepts_messages. However, it never explicitly states when to use send_message instead of run_thronglet for a new session, nor does it mention cancel_thronglet as an alternative to steer, leaving some sibling selection implicit.

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