Skip to main content
Glama
Sign In
opencode-subagent-mcp

opencode-subagent-mcp

by sebstaq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Continue an opencode subagent

send_message

Resume a finished or interrupted opencode subagent by agent_id to send follow-up work. It continues with full prior history and returns a new final report.

Instructions

Send a follow-up message to a finished opencode subagent by agent_id. It resumes with its full previous history (and its worktree, if one was kept) and returns its new final report. Also works for agent_ids from before a restart of the MCP server or Claude Code session, and for agents that were interrupted by such a restart.

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_id": "<agent_id>",
      "message": "<message>"
    },
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYes
agent_idYes
max_turnsNo
run_in_backgroundNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does disclose meaningful behavior: the subagent resumes with its full prior history, its worktree is preserved if one was kept, and the call returns a new final report. It also discloses cross-restart persistence, a real operational trait. It omits what max_turns does by default or that run_in_background makes the call async.

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?

Three sentences, zero filler, with the core verb and the agent_id anchor front-loaded. The trailing restart sentence is a worthwhile edge case rather than padding, though it could be tightened.

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

Completeness3/5

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

For a stateful, mutating tool with no annotations and no output schema, the description does tell the agent what comes back ("its new final report") and how state is restored. What's missing is the behavior of the two optional control parameters (max_turns, run_in_background), which materially change how the call behaves.

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

Parameters2/5

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

Schema description coverage is 0% across 4 parameters, so the description must compensate. It clarifies `agent_id` semantics (finished agents, agents from before a restart) but says nothing about `max_turns` or `run_in_background`, leaving half the parameters entirely unexplained anywhere.

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?

States a specific verb and resource ("Send a follow-up message to a finished opencode subagent by agent_id") and immediately distinguishes itself from siblings like `agent` (which starts a new one) and `stop`/`wait`. An agent can tell exactly what this does 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?

The description scopes usage clearly (a *finished* subagent) and adds a valuable edge case: agent_ids that predate an MCP/Claude Code restart or that were interrupted by one. However, it never explicitly names alternatives or states when *not* to use it (e.g., use `agent` for a fresh subagent, `stop` to cancel).

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