Skip to main content
Glama

User Preferences & Memory

preferences
DestructiveIdempotent

Manage user preferences and memory settings. Data is encrypted at rest (AES-256-GCM) in isolated per-user directories.

Actions:

  • get: report whether memory is enabled and return saved preferences.

  • set: save preferences; memory_enabled must be true before any preferences, monitors, or strategies can be stored, and requires explicit user consent.

  • delete: permanently erase all stored user data (GDPR Article 17).

Related: monitor, strategy.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "preferences"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNo'short', 'brandable', 'keyword' (set only)
actionNo'get', 'set', or 'delete'. Defaults to 'get' if not specified.
budgetNo'low', 'medium', 'high' (set only)
industryNoIndustry type (set only)
memory_enabledNo'true' to enable memory, 'false' to disable. Must be enabled before using monitors or strategies. (set only)
preferred_tldsNoComma-separated TLDs, e.g. 'com,net,io' (set only)
exclude_hyphensNo'true' or 'false' (set only)
exclude_numbersNo'true' or 'false' (set only)

Output Schema

NameRequiredDescriptionDefault
dataNoSaved preference data (get only, when memory is enabled)
messageNoHuman-readable result message
successNoWhether the request was successful
memory_enabledNoWhether memory is enabled for this user
monitors_countNoNumber of active monitors (get only)
monitors_summaryNoMonitor overview (get only, when monitors_count > 0)
strategies_countNoNumber of active strategies (get only)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedOutput schema / required
      Removed value: -[
      -  "success"
      -]
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds real context beyond them: AES-256-GCM encryption at rest, per-user isolated directories, an explicit consent gate, and that delete is a permanent GDPR Article 17 erasure. It stops short of describing what get returns when memory is disabled, but the output schema covers return shape.

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?

Front-loaded purpose sentence, then a scannable action list, then a related-tools pointer. Nearly every sentence carries information; the encryption detail and the GDPR citation are both earning their place as behavior the agent would otherwise not know.

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 multi-action tool with eight optional parameters, an output schema, and full schema coverage, the description supplies the action model, prerequisites, side effects, and alternatives. Nothing material is missing for correct invocation.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, and the description genuinely adds meaning: it explains the memory_enabled prerequisite that governs whether any of the set-only fields can take effect, and it marks which action each field belongs to. It does not add format guidance for values like preferred_tlds, but the schema already does.

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?

Names a specific resource (user preferences and memory) and decomposes it into three explicit actions (get/set/delete) with what each does. The 'Related: monitor, strategy' line signals what this tool is not, so an agent can distinguish it from sibling tools without opening schemas.

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?

Gives clear context for each action and an ordering prerequisite (memory_enabled must be true before preferences, monitors, or strategies can be stored) plus a consent requirement. It does not explicitly say when to pick this over monitor or strategy, but the 'Related' pointer and the gating rule make the selection clear enough.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.