Save a manual note or memory to your personal store so AI assistants can retrieve it later. Add a source label and metadata to improve indexing and search.
Add a manual memory/note to your personal memory store.
Args: content: The text content to remember source: Source label for this memory (default: 'manual') metadata: Optional key-value metadata to attach
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | manual | |
| content | Yes | ||
| metadata | No |
Changes observed during successful MCP inspections.
v0.4.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It confirms a write/add operation but says nothing about persistence, duplicate handling, permissions, or what the add returns. For an unannotated mutation tool this is a real gap.
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 purpose sentence is front-loaded and the Args block is compact, one line per parameter. There is little waste, though the Args duplication of the schema is somewhat redundant.
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 3-param tool with no output schema and no annotations, the description covers the inputs but omits behavioral context an agent would want (persistence, return value, duplicate handling). Adequate but with clear gaps.
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%, so the description meaningfully compensates by documenting all three params: content ('text to remember'), source (with its 'manual' default), and metadata ('optional key-value metadata'). The metadata entry is thin (no expected keys or format), so it clarifies the basics but not the details.
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?
States a specific verb ('add') and resource ('manual memory/note') with the target store ('personal memory store'). It is clear what the tool does, though it does not explicitly distinguish itself from the sibling search_memoreei. The word 'manual' implicitly separates it from the many sync_*/import_* siblings.
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 term 'manual' implies this is for user-entered notes as opposed to synced or imported data, giving implied usage context. However, there is no explicit when-to-use/when-not-to-use guidance and no alternative tool is named, leaving the agent to infer the boundary against the sync/import siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.