cortex_recallNarrative synthesis of what the user's memory knows about a topic, with the current state and what was superseded. Use it for questions like 'what do you know about X' or 'what is the current state of X'.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by clarifying the behavioral output: a narrative synthesis that distinguishes current state from superseded state, which goes beyond the annotations and helps set agent expectations.
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 description is compact, front-loaded with the core behavior, and uses one practical example sentence. Every clause earns its place without redundant restating of the tool name or title.
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 single-parameter read-only tool, the description fully explains what the tool does, what input it expects, and what kind of output it produces. Although there is no output schema, the description states that it returns a narrative synthesis with current and superseded state, which is sufficient for an agent to invoke it correctly.
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?
The schema provides only the parameter name 'query' with type string and no description. The tool description compensates by explaining that the query should be a topic or question about what the memory knows, with concrete example phrasings. This adds meaningful semantic guidance despite the schema's 0% description coverage.
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?
The description states a specific action ('Recall & synthesize') and a clear resource ('the user's memory'), and explains the output format as a narrative synthesis including current state and superseded state. The examples ('what do you know about X') make the purpose immediately recognizable and distinguish it from sibling tools like cortex_write or cortex_forget.
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 description gives explicit usage examples for when to invoke this tool, such as 'what do you know about X' or 'what is the current state of X'. It does not explicitly state when not to use it or name alternatives, but the context is clear enough for an agent to route queries about memory recall to this tool.
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.
Search and recall both retrieve from memory and could be confused, but the descriptions distinguish search as returning results and recall as producing a narrative synthesis. cortex_write_status and cortex_conflicts also both touch conflicts, but one is tied to a specific queued write, so agents can mostly choose correctly.
Most tools share a cortex_ prefix and verb-like names such as write, forget, and recall, but cortex_conflicts is a noun, cortex_write_status is a verb+noun compound, and fetch/search lack the prefix. The convention is readable but not consistently applied.
Seven tools cover the memory domain without bloat. Each tool maps to a distinct operation, and the count feels well-scoped for a persistent memory server.
The surface covers the core memory lifecycle: write, search/recall, fetch by id, delete, and conflict/status inspection. No obvious dead ends or missing operations for the stated purpose.