Retrieve persistent project facts and rules from associative memory in under 100 microseconds. Query by key or semantic concept to restore context for AI coding agents.
Recall a persistent fact or project rule from associative neural memory in <100 microseconds.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Key or semantic concept to recall |
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 carries the full behavioral burden. It usefully discloses a performance trait (<100 microseconds) and the memory type, but says nothing about miss behavior, permission/scope requirements, or confirmation that this is a safe read-only operation.
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 with zero waste; the action, target, source, and performance trait are all delivered compactly.
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 simple one-parameter read tool with no annotations and no output schema, the description covers the essentials, but it omits what happens when nothing matches and whether the lookup is scoped or permissioned.
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 a single documented parameter, so the baseline is 3. The description hints that the query can be a key or semantic concept but adds no format, matching, or syntax detail beyond the schema.
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 clear verb (Recall) and resource (persistent fact or project rule) drawn from a named store (associative neural memory). It is distinguishable from cortex_memory_remember and cortex_memory_erase by verb, though it does not explicitly differentiate itself from the other lookup 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 phrasing implies when to reach for this tool (retrieving stored facts/rules), but there is no explicit when-to-use versus alternatives like cortex_symdex_lookup or cortex_prompt_lookup, and no when-not guidance or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.