Saves a durable memory entry after retrieval; reuse the same idempotency key when retrying so writes stay consistent and duplicate records are avoided.
Save a durable memory after search. Reuse the idempotency key for retries.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| tags | No | ||
| title | Yes | ||
| source | No | ||
| summary | No | ||
| metadata | No | ||
| space_id | No | ||
| confidence | No | Confidence score from 1 to 5. | |
| session_id | No | ||
| category_id | No | ||
| idempotency_key | Yes | ||
| auto_prefetch_level | No | normal |
Changes observed during successful MCP inspections.
v2.2.0Input schema / properties / category_id / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / category_id / defaultAdded value: +nullInput schema / properties / category_id / typeRemoved value: -"string"Input schema / properties / idempotency_keyAdded value: +{
+ "title": "Idempotency Key",
+ "type": "string"
+}Input schema / properties / metadataAdded value: +{
+ "anyOf": [
+ {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Metadata"
+}Input schema / properties / session_idAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Session Id"
+}Input schema / properties / sourceAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Source"
+}Input schema / properties / space_idAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Space Id"
+}Input schema / requiredPrevious value: -[
- "category_id",
- "title",
- "body"
-]New value: +[
+ "title",
+ "body",
+ "idempotency_key"
+]Output schema / (root)Previous value: -{
- "additionalProperties": true,
- "title": "create_memoryDictOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. It mentions durability and idempotent retries, but it does not disclose permissions, duplicate-handling behavior beyond retry keys, whether creation is reversible, or what the tool returns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short, front-loaded sentences with no wasted language. The purpose and retry instruction are stated immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a complex 12-parameter mutation tool with no annotations and no output schema. The description does not explain how to populate the three required fields or the optional fields, nor does it describe the creation effect, making it inadequate for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 8%, and the description explains only idempotency_key. It leaves title, body, tags, source, summary, metadata, space_id, confidence, session_id, category_id, and auto_prefetch_level unexplained, despite low schema coverage requiring the description to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: "Save a durable memory." It also adds timing context with "after search," but it does not explicitly distinguish creation from the sibling update_memory tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"After search" gives implied usage context, and "Reuse the idempotency key for retries" gives retry guidance. However, it does not state when not to use this tool, how it differs from update_memory, or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.