docs(api-reference): address reviewer comments on search defaults table and retrieval_criteria shape

- search-memories.mdx: collapse V1/V2/V3 comparison table to a single "Default" column showing current (v3) values only (threshold 0.1, rerank false, top_k 10)
- organizations-projects.mdx: replace bogus {role, content} retrieval_criteria examples with the correct {name, description, weight} shape, mirroring the canonical criteria-retrieval.mdx examples; update prose to name the three required fields

docs/api-reference/memory/search-memories.mdx

@@ -20,11 +20,11 @@ The `filters` object supports complex logical operations (AND, OR, NOT) and comp
 
 ### Search parameter defaults
 
-| Parameter | V1/V2 | V3 |
-| --- | --- | --- |
-| `top_k` | Supported (default 10) | Supported (1-1000, default 10) |
-| `threshold` | V1: not supported / V2: default `0.3` | Default `0.1` (pass `0.0` to disable) |
-| `rerank` | Default `false` | Default `false` (pass `true` to enable) |
+| Parameter | Default |
+| --- | --- |
+| `top_k` | `10` (range 1–1000) |
+| `threshold` | `0.1` (pass `0.0` to disable) |
+| `rerank` | `false` (pass `true` to enable) |
 
 <CodeGroup>
 ```python Platform API Example

docs/api-reference/organizations-projects.mdx

@@ -101,8 +101,8 @@ client.project.update(multilingual=True)
 # Set retrieval criteria to control which memories are surfaced in search
 client.project.update(
     retrieval_criteria=[
-        {"role": "user", "content": "Only retrieve memories relevant to the current topic"},
-        {"role": "assistant", "content": "Prioritize recent and frequently accessed memories"}
+        {"name": "relevance", "description": "How directly relevant this memory is to the current topic or user query", "weight": 3},
+        {"name": "access_frequency", "description": "How often this memory has been accessed or surfaced recently", "weight": 1}
     ]
 )
 
@@ -122,13 +122,26 @@ client.project.update(
 
 #### Set Retrieval Criteria
 
-`retrieval_criteria` is a per-project list of dictionaries (`List[Dict]`) that shapes how memories are ranked and filtered during search. Each dictionary specifies a criterion that the retrieval engine applies when deciding which memories to surface. Use this to focus retrieval on topic-relevant or role-specific memories:
+`retrieval_criteria` is a per-project list of dictionaries (`List[Dict]`) that shapes how memories are ranked and filtered during search. Each dictionary has three fields: `name` (identifier), `description` (interpreted by the LLM to score each memory), and `weight` (relative influence on the final score). Use this to focus retrieval on intent-aligned or signal-specific memories:
 
 ```python
 client.project.update(
     retrieval_criteria=[
-        {"role": "user", "content": "Only retrieve memories directly relevant to the user's current query"},
-        {"role": "assistant", "content": "Prefer memories that have been accessed recently"}
+        {
+            "name": "joy",
+            "description": "Measure the intensity of positive emotions such as happiness, excitement, or amusement expressed in the memory. A higher score reflects greater joy.",
+            "weight": 3
+        },
+        {
+            "name": "curiosity",
+            "description": "Assess the extent to which the memory reflects inquisitiveness or interest in exploring new information. A higher score reflects stronger curiosity.",
+            "weight": 2
+        },
+        {
+            "name": "access_frequency",
+            "description": "How often this memory has been accessed or surfaced recently.",
+            "weight": 1
+        }
     ]
 )
 ```