diff --git a/.github/agents/adr-writer.agent.md b/.github/agents/adr-writer.agent.md
index 6aaf1fca1bc..5141a552f02 100644
--- a/.github/agents/adr-writer.agent.md
+++ b/.github/agents/adr-writer.agent.md
@@ -82,20 +82,11 @@ Example: `docs/adr/0001-use-postgresql-for-primary-storage.md`
 
 ## Writing Quality Standards
 
-#### Context (3–5 sentences)
-- Problem and constraints (technical, organizational, timeline)
-- Codebase state at decision time; problem space, not implementation
+Beyond the per-section length hints in the template:
 
-#### Decision (2–4 sentences)
-- Active voice: "We will use X because Y"
-- Name primary driver (performance, simplicity, cost) and pattern/principle if applicable
-
-#### Alternatives Considered (2–4 sentences each)
-- **≥2 genuine alternatives** (no strawmen); for each: what, why considered, why rejected
-
-#### Consequences
-- **Positive**, **Negative**, **Neutral**: real benefits, costs, and side effects
-- ≥2 per category for non-trivial decisions
+- **Decision** — active voice ("We will use X because Y"); name the primary driver (performance, simplicity, cost).
+- **Alternatives** — ≥2 genuine options, no strawmen; each: what, why considered, why rejected.
+- **Consequences** — ≥2 per Positive/Negative/Neutral category for non-trivial decisions.
 
 ## Procedure: Writing a New ADR
 
diff --git a/.github/agents/contribution-checker.agent.md b/.github/agents/contribution-checker.agent.md
index 4158b46b7b5..fd076575951 100644
--- a/.github/agents/contribution-checker.agent.md
+++ b/.github/agents/contribution-checker.agent.md
@@ -85,17 +85,13 @@ Return a single **JSON object** (no extra text):
 }
 ```
 
-Where:
-- `verdict` is one of: `🔴`, `⚠️`, `🟡`, `🟢`, `❓`
-- `on_topic` is `yes`, `no`, or `unclear`
-- `focused` is `yes` or `no`
-- `deps` is `yes` or `no`
-- `tests` is `yes` or `no`
-- `lines` is the total lines changed (integer)
-- `quality` is one of: `spam`, `needs-work`, `lgtm`, `no-guidelines`
-- `existing_labels` is an array of the PR's current labels, or `[]` if none
-- `title` is the PR title
-- `author` is the PR author's username
+Field values:
+- `verdict`: `🔴`, `⚠️`, `🟡`, `🟢`, or `❓`
+- `on_topic`: `yes`, `no`, or `unclear`
+- `focused`, `deps`, `tests`: `yes` or `no`
+- `lines`: total lines changed (integer)
+- `quality`: `spam`, `needs-work`, `lgtm`, or `no-guidelines`
+- `existing_labels`: array of the PR's current labels, or `[]`
 
 ### Comment Field