memory_key_facts_rememberStore a durable key fact in persistent memory with its source and confidence, so you can recall it across sessions and chats.
Store a durable key fact in persistent memory, with its source and confidence.
| Name | Required | Description | Default |
|---|---|---|---|
| fact | Yes | The fact text to remember | |
| tags | No | Optional topic tags | |
| source | No | Origin label for this fact (defaults to 'mcp') | mcp |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and destructiveHint=true, so the write profile is already covered by structured data. The description usefully adds that the write is 'durable' and lands in 'persistent memory', but it does not explain the destructive aspect the annotation implies — whether an existing fact of the same key is replaced or a duplicate is created, which is exactly the behavior an agent needs before writing.
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: verb, object, target store. Nothing is padded. It loses a point only because the trailing 'with its source and confidence' clause spends words on a field the schema does not actually offer.
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-parameter write tool with no output schema, the description covers the core action but omits what the agent most needs: duplicate/overwrite semantics (relevant given destructiveHint=true) and what the call returns (an id, a confirmation). Annotations carry the safety profile, so this is adequate rather than broken.
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% with three documented parameters (fact, tags, source), so the baseline is 3. The description adds no format or syntax guidance, and it references a 'confidence' value that does not exist in the schema — a small inaccuracy rather than added semantic value.
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 and resource: 'Store a durable key fact in persistent memory.' That is enough to tell it apart from the read-oriented siblings (retrieve, stats) and the destructive forget. However, it never names or contrasts itself with the closest sibling, memory_key_facts_update, so the agent must infer the create-vs-update boundary from the tool name alone.
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?
There is no when-to-use guidance at all: nothing says whether recalling/retrieving an existing fact should precede a remember, whether storing an already-known fact duplicates or overwrites, or when to prefer update over remember. The only signal is the tool name and the word 'durable', which the agent must interpret unaided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.