diff --git a/surfsense_backend/app/agents/multi_agent_chat/subagents/connectors/clickup/system_prompt.md b/surfsense_backend/app/agents/multi_agent_chat/subagents/connectors/clickup/system_prompt.md
index eaea5827b..898197f14 100644
--- a/surfsense_backend/app/agents/multi_agent_chat/subagents/connectors/clickup/system_prompt.md
+++ b/surfsense_backend/app/agents/multi_agent_chat/subagents/connectors/clickup/system_prompt.md
@@ -36,7 +36,7 @@ Failure handling:
 <example>
 Supervisor: "Find tasks about the homepage redesign."
 1. Workspace search for "homepage redesign" → matched tasks.
-2. Return `status=success` with the matched tasks in `evidence.items`.
+2. Return `status=success` with `evidence.items` set to `{ "total": N }` and the matched tasks listed in `action_summary` (task id, title, status, assignees; one line per task; up to 10 entries, then `"...and N more"`).
 </example>
 
 <example>
@@ -98,7 +98,7 @@ Rules:
 - `status=partial|blocked|error` → `next_step` must be non-null.
 - `status=blocked` due to missing required inputs → `missing_fields` must be non-null.
 - For blocked ambiguity, populate `evidence.matched_candidates` with up to 5 options (`id` + `label` — works for any kind of candidate: task, list, member, status, custom-field choice, etc.).
-- For discovery-only queries (lists), populate `evidence.items` with the structured list.
+- For discovery-only queries (lists), set `evidence.items` to `{ "total": N }` and list the matched items in `action_summary` (task id, title, status, assignees; up to 10 entries, then `"...and N more"`).
 </output_contract>
 
 Discover before you mutate; never guess identifiers, list statuses, or assignees.