Skip to main content
Glama

Cortex

by io.github.FilippoPilo

Save memory

cortex_write

Save to the user's persistent memory (Cortex), ON YOUR OWN INITIATIVE while the conversation goes on, without waiting to be asked: decisions and the reason behind them, stable facts about the person and their work, preferences and constraints they state, conclusions reached after effort, mistakes made and what they cost. A good memory is one still useful in a month. Say in a few words what you saved, so the user can answer 'do not keep that'. Proposing costs nothing: the server rejects duplicates by itself, and a refused write is not an error. If unsure whether something matters, ask the user one single question. Never save passwords, tokens, keys or card numbers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNo
basisNoOrigine dell'informazione: 'observed' se letta direttamente da una fonte (documento, output di uno strumento, dato reale), 'inferred' se e' una deduzione o una stima. Registrata al salvataggio e restituita al richiamo.
titleYesShort title
claimsNoOpzionale. Fatti atomici gia strutturati, uno per decisione o affermazione: se li passi, il rilevamento dei conflitti li usa direttamente invece di estrarli dal testo. Esempio: {subject: 'Project Vega', predicate: 'adotta', object: 'Redis'}.
contentYesText to remember, in the user's language

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only readOnlyHint=false and openWorldHint=true available, the description adds valuable behavioral context: duplicate writes are rejected server-side, a refused write is not an error, and sensitive data like passwords must never be saved. It also surfaces the 'proposing costs nothing' behavior, which helps an agent calibrate risk.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than a minimal API summary, but it encodes important agent policy rather than repeating schema details. It is front-loaded with the core imperative and each sentence contributes meaningful guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a memory-write tool with no output schema, the description covers the essential operating context: what to save, how to handle uncertainty, duplicate behavior, and security exclusions. It is complete enough for an agent to call the tool correctly in real conversations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is high (80%), and the schema already documents title, content, basis, and claims. The description adds no parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Save to the user's persistent memory (Cortex)') and makes the proactive policy explicit. It is clearly distinct from siblings like cortex_recall, cortex_forget, and cortex_conflicts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives strong context for when to save: on the agent's own initiative, while the conversation goes on, without waiting to be asked, and it enumerates what is worth saving. It does not explicitly name the alternative tools, but the intended use case is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Cortex toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

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.

Naming Consistency3/5

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.

Tool Count5/5

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.

Completeness5/5

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.

Resources