Store or cleanly overwrite persistent architectural facts and project rules in neural memory, helping AI coding agents recall key project context across sessions.
Store or cleanly overwrite a persistent architectural fact or project rule using Titans + DeltaNet-2 neural memory.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Concept or variable identifier | |
| value | Yes | Fact or value to memorize | |
| category | No | architecture |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full behavioral burden. It does disclose two valuable traits: the write is persistent and the overwrite is 'clean' (idempotent upsert rather than an error on duplicate keys), plus the backing store. It omits scope/namespace, whether the value fully replaces prior content, and any permission or size constraints.
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 that leads with the action and scope. No filler, no redundancy.
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 mutation tool with no annotations and no output schema, the description covers the core behavior (persistent upsert) but leaves gaps: no return/confirmation semantics, no scoping model, and no guidance on the undocumented category parameter. Adequate but not complete.
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 67%: key and value are documented in-schema, while category has only a default ('architecture') and no description. The phrase 'architectural fact or project rule' hints at what category values might be, but the description does not explain the category parameter or the key format.
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?
Names a specific verb pair (store/overwrite) and resource (persistent architectural fact or project rule), and the 'remember' framing clearly positions it against the recall/erase siblings. It stops short of explicitly differentiating itself from siblings like cortex_symdex_lookup or cortex_sieve_compact.
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?
No statement of when to use this tool versus cortex_memory_recall, cortex_memory_erase, or the other memory siblings. The only usable signal is the implied upsert ('store or cleanly overwrite'), which is behavioral rather than a selection guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.