Store a durable memory under a key you choose, so you can recall it in a future session. The value is text (notes, JSON, state, or URLs pointing to your own files) and is private to you. Overwrites an existing memory with the same key.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Key to store this memory under (letters, digits, and . _ : -). | |
| value | Yes | The memory content: text, JSON, notes, or URLs to your own files. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already disclose write (readOnlyHint=false), idempotent (idempotentHint=true) and non-destructive behavior. The description goes further by stating that an existing memory with the same key is overwritten, which flags data loss, and that memories are durable and private to the caller.
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?
Three short sentences, no filler, with the core action and key choice front-loaded and the overwrite caveat last where it matters.
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 write tool with full schema coverage and annotations covering the safety profile, plus no output schema to explain, the description covers durability, privacy, and overwrite semantics adequately. Only the explicit sibling routing is missing.
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 coverage is 100%, so both parameters are already documented, including the key character constraints. The description's note that value may be notes, JSON, state, or URLs roughly restates the schema, adding little syntax beyond the baseline.
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 (store) and resource (durable memory under a chosen key), plus the payoff of cross-session recall. It doesn't explicitly name the sibling recall/forget/list_memories tools, so an agent must infer the write-side role from context.
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?
Usage is implied: persist information you want available in a future session. There is no explicit statement of when not to use it versus recall, forget, or list_memories, so routing among the memory siblings is left to inference.
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.