Store a memory, fact, decision, or preference for later retrieval.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Tags for categorization | |
| type | Yes | Type of memory | |
| content | Yes | Content of the memory | |
| metadata | No | Additional metadata | |
| source_session_id | No | Optional reference to source session |
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | Human-readable tool result text. |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "message": {
+ "description": "Human-readable tool result text.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "message"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, so the write-and-safe profile is covered structurally. The description adds nothing beyond that: it does not mention idempotency behavior, duplicate handling, persistence scope, or auth requirements, despite idempotentHint=false making duplicate-write behavior a real question.
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?
A single front-loaded sentence with zero filler and the write purpose stated immediately. It is efficient, though the brevity is partly what leaves the usage and behavioral gaps unaddressed.
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?
An output schema exists, so return values need no explanation, and 100% schema coverage plus annotations carry the structural weight. The description is adequate for invoking the tool correctly, with the only real gap being when-to-use routing among the many sibling save/checkpoint/search tools.
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 100%, so all five parameters (content, type, tags, metadata, source_session_id) are already documented in the schema. The description names a few memory categories that partly mirror the type enum but adds no format, constraint, or interaction detail beyond the schema, making the baseline 3 correct.
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 (Store) and resource (memory, fact, decision, preference), so the agent understands this is a write operation for persisting knowledge. It clearly contrasts in nature with read-oriented siblings like palim_search or palim_get_context, but never names an alternative explicitly, keeping it just short of a 5.
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?
The phrase 'for later retrieval' weakly implies the purpose, but there is no guidance on when to choose this tool over palim_save_context, palim_checkpoint, or palim_save_session, nor any stated exclusions or prerequisites. The agent must infer the routing decision entirely on its own.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.