Automatically extract key facts, preferences, and decisions from conversation messages and save them as memories for future reference.
Auto-extract memorable facts/preferences/decisions from a list of conversation messages and store them as memories.
| Name | Required | Description | Default |
|---|---|---|---|
| project | No | ||
| messages | Yes | List of {role, content} messages, or a JSON string. | |
| max_memories | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the core mutation (storing memories) but does not mention side effects like duplication, overwriting, or the impact on existing memories. It also omits details about the max_memories limit and whether the operation is deterministic. The description is honest about the main action but lacks depth.
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 a single, efficient sentence that front-loads the purpose with no unnecessary words. It is highly concise and well-structured.
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 tool that extracts and stores memories from a message list, the description is too sparse. It does not explain the 'project' parameter, the 'max_memories' limit, or what the tool returns (e.g., whether it returns the created memories). An agent would need to inspect the schema further and make assumptions about side effects. The description is incomplete for reliable 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 33% (only 'messages' has a description). The tool description adds nothing about 'project' or 'max_memories', leaving the agent without any guidance on how to set these parameters or what they control. The description fails to compensate for the low schema coverage.
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 action ('extract'), a specific resource ('conversation messages'), and a clear outcome ('store them as memories'). This clearly differentiates it from sibling tools like remember (direct storage) and recall (retrieval), making the purpose unambiguous.
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 description provides clear context: use this tool when you have a list of conversation messages and want to extract memories from them. However, it does not explicitly contrast with alternatives like remember or state when not to use it, though the context is clear enough for most agents.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.