Skip to main content
Glama

send_agent_message

Send new input to a completed agent conversation to start a new job without resending prior messages; specify provider, model, and conversation ID, with permissions and concurrency enforced.

Instructions

完了した会話へ追加入力して新しいジョブを開始する。native会話は新しい入力だけを同じ子へ送る(過去入力を再送しない)。provider/cwd/権限/隔離方式は変更不可。モデル・Effortは毎回明示し再検証する。同時ターンは不可

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": {
      "provider": "<provider>",
      "model": "<model>",
      "task": "<task>",
      "conversation_id": "<conversation_id>"
    },
    "name": "send_agent_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNo
roleNo
taskYes
filesNo
modelYes必須。許可済みの取得済みモデルID
effortNoEffort対応モデルでは必須。対応・許可済みの値のみ
contextNo
providerYesプロバイダーID
permissionNo省略時full-access(OSユーザー権限の範囲で標準編集・シェル)。read-only/workspace-writeは既存のCLI標準制限。brokeredではread-only/workspace-writeの明示が必須
timeout_msNo
json_schemaNo
conversation_idYes
include_detailsNo同期結果に使用量・実行メタデータを含める。既定false。非同期結果はget_agentで指定
notify_progressNo同期実行の進捗通知を送る。既定false。バックグラウンド実行では通知しない
output_instructionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and delivers: provider/cwd/permission/isolation cannot be changed on resume, model and effort must be re-specified and are re-validated each call, native conversations resend only new input, and concurrent turns are rejected. It does not say whether the call blocks or returns a job handle, which is the main remaining behavioral gap.

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?

Extremely dense and front-loaded – purpose first, then the behavioral constraints in terse clauses. Every sentence carries information, though the clipped phrasing (e.g. '同時ターンは不可') reads as notes rather than a polished spec.

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 15-parameter mutation tool with no annotations and no output schema, the description covers the critical invariants but leaves the sync/async contract and most optional parameters unexplained. It is adequate to avoid misuse of the core fields, not adequate to call the tool confidently in full.

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 coverage is only 40% across 15 parameters, so the schema does not carry the load. The description adds real constraints for provider, cwd, permission, isolation, model, and effort (immutability / must-respecify), but says nothing about task, role, files, context, json_schema, timeout_ms, or conversation_id, leaving most parameters without guidance.

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+resource: send additional input to a completed conversation and start a new job. The scope ('完了した会話へ', i.e. not new conversations) implicitly separates it from start_agent, but no sibling is named explicitly.

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

Usage Guidelines3/5

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

The precondition (conversation must be completed) and the prohibition on concurrent turns imply when to use it, but there is no explicit routing guidance such as 'use start_agent for a new conversation' or 'use wait_agents to collect results'.

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