List the most recently saved memories (newest first), e.g. to review what was stored.
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_recent_memories"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| type | No | ||
| limit | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full disclosure burden. It does add real behavioral detail beyond the schema: the result ordering (newest first) and the 'most recently saved' scoping. However, it omits pagination/truncation behavior beyond the limit, permissions, and the shape of returned items, which matters for an unannotated read tool.
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 sentence with the resource and ordering front-loaded and no redundant wording. Nothing needs to be cut and the key operational fact (newest first) arrives 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?
For a two-parameter tool with no annotations, no output schema, and undocumented parameters, the description should describe the type filter's effect and what a returned memory looks like. It covers ordering and intent but leaves the parameters and return shape entirely unspecified.
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 0% for two parameters, so the description must compensate and does not. Neither the 'type' enum (episodic/semantic/procedural/profile) nor 'limit' (default 10) is mentioned, leaving the agent to infer that type is an optional filter and limit caps result count.
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 gives a specific verb ('List') and resource ('most recently saved memories') plus the sort order ('newest first'), which lets an agent recognize this as a recency-ordered listing rather than a semantic search. It does not name or contrast any sibling such as recall or get_timeline, so differentiation is left implicit.
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?
'e.g. to review what was stored' implies a usage context (browsing recent storage rather than targeted retrieval), but there is no explicit when-not guidance and no named alternative for query-based retrieval. The agent must infer that recall/search_temporal are the tools for filtered or semantic lookup.
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.