ready for merge tool description

docs/operations.md

@@ -37,7 +37,7 @@ A task ends `merged` or `discarded`; either way its sessions are stopped, its sn
 
 A task's summary is what its agent writes, before the task closes, about the whole task: what it set out to do, what was built or tried, the key decisions and why, and what was left out. The agent sets it with the `set_task_summary` MCP tool (`internal/agents/summary.go`), any time while the task is active; each call replaces `tasks.summary` and records a `task.summary` event carrying it, which the transcript shows as a note. The Merge turn's prompt and the discard turn's prompt (`summaryRequest`) both ask for it. Turn summaries don't stand in for it: each covers only its own turn, and a merged task's last one is always the Merge turn's. Tasks closed before the column existed have none. `sqlite3 byre.db "SELECT id, status, summary FROM tasks WHERE status != 'active' ORDER BY closed_at DESC LIMIT 5"` shows recent ones.
 
-An implementer says its task is ready to merge with the `ready_for_merge` MCP tool (`internal/agents/ready.go`), whose `overview` covers the whole task for a human switching between tasks: a summary, tradeoffs and compromises, what was not done, and future TODOs. Each call records a `task.ready` event carrying it, which the lead gets as a signal and the transcript draws as a bubble (`ReadyBubble` in `mac/Sources/Byre/Chat.swift`) headed "ready for merge". The latest one, while the task is active and no snapshot other than an answer snapshot has been taken since it (newer work the overview doesn't cover), is drawn like an open question (the warn tint and border) and carries small Merge and Discard buttons that act like the header's, confirmation dialogs included; earlier ones are drawn like an answered question (the faint warn tint), without buttons. Recording it changes nothing else. byre asks for it (`readyPrompt`, sent as a byre message) when a task's state goes to `idle` (`Manager.Observe` calls `promptReady`) and the latest non-answer snapshot's review is `done` or `skipped`, once per snapshot. It checks and sends under the session's delivery lock (the one human messages and answers take), and only to an agent that isn't running, so the prompt never queues behind a turn that could add unreviewed work; `tasks.ready_prompt_n` holds the last snapshot asked about, set only once the prompt's turn started, so turns that change no files don't ask again and a new snapshot does. It doesn't ask for workflow stage tasks, a task with a merge after review set, or a review that failed, and it skips the `reviewing` → `idle` change of a review with findings, since those go to the agent; the turn that answers them asks once it ends without new work. The prompt tells the agent not to call the tool, and to say what's left, when the task isn't ready.
+An implementer says its task is ready to merge with the `ready_for_merge` MCP tool (`internal/agents/ready.go`), whose `overview` covers the whole task for a human switching between tasks: a summary, tradeoffs and compromises, what was not done, and future TODOs. Its description tells the agent to call it only once the review of its most recent changes has come back, never in the same turn as a change or while that review is pending. Each call records a `task.ready` event carrying it, which the lead gets as a signal and the transcript draws as a bubble (`ReadyBubble` in `mac/Sources/Byre/Chat.swift`) headed "ready for merge". The latest one, while the task is active and no snapshot other than an answer snapshot has been taken since it (newer work the overview doesn't cover), is drawn like an open question (the warn tint and border) and carries small Merge and Discard buttons that act like the header's, confirmation dialogs included; earlier ones are drawn like an answered question (the faint warn tint), without buttons. Recording it changes nothing else. byre asks for it (`readyPrompt`, sent as a byre message) when a task's state goes to `idle` (`Manager.Observe` calls `promptReady`) and the latest non-answer snapshot's review is `done` or `skipped`, once per snapshot. It checks and sends under the session's delivery lock (the one human messages and answers take), and only to an agent that isn't running, so the prompt never queues behind a turn that could add unreviewed work; `tasks.ready_prompt_n` holds the last snapshot asked about, set only once the prompt's turn started, so turns that change no files don't ask again and a new snapshot does. It doesn't ask for workflow stage tasks, a task with a merge after review set, or a review that failed, and it skips the `reviewing` → `idle` change of a review with findings, since those go to the agent; the turn that answers them asks once it ends without new work. The prompt tells the agent not to call the tool, and to say what's left, when the task isn't ready.
 
 Agents find closed tasks with the `search_closed_tasks` MCP tool, which task agents get for their own project and the lead for one project (`project_id`) or all: a case-insensitive substring match of `query` on title, merge title, TODO item, summary and merge commit (`Store.SearchClosedTasks`), newest closed first, at most `limit` (default 20, at most 100), each with its id, outcome, merge commit, close time, creator, titles, TODO item, fork source and summary. The lead reads a closed task's transcript with `read_transcript`. There is no closed-task list in the UI; the human asks the lead.
 

internal/agents/ready.go

@@ -26,7 +26,8 @@ func (m *Manager) readyForMergeTool(l *live) mcp.Tool {
 		Name: "ready_for_merge",
 		Description: "Tell the human this task is ready to merge, with an overview of the whole task: all of the branch's work, not just what changed since your last call or the last discussion. " +
 			"Write it for someone jumping between tasks who hasn't followed this one: a summary of what the change does, the tradeoffs and compromises made, what was not done, and follow-up work for later. " +
-			"byre shows it in the task's transcript and passes it to the human's lead agent.",
+			"byre shows it in the task's transcript and passes it to the human's lead agent. " +
+			"Call it only once the review of your most recent changes has come back: byre reviews the work after each turn that changes files and messages you when that review finishes, so never call it in the same turn as a change, or while a review of your latest work is pending.",
 		InputSchema: json.RawMessage(`{
 			"type": "object",
 			"properties": {