Skip to main content
Glama

Update my preferences

preferences_update
Idempotent

Changes your own preferences. Send only what changes: language, theme (saved as the account default for new devices), calendar, notifications ([{category, email?, telegram?}] for categories that are live), contact_channel (email, phone, whatsapp, telegram or null) and marketing_opt_out:true to stop marketing messages. reset_notifications:true restores the default notification settings and needs confirm:true. Agreeing to marketing messages is not possible here (website only). Pass expected_rev from preferences_get to avoid overwriting a newer change.

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_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNoAccount default theme for new devices.
confirmNoRequired with reset_notifications.
calendarNoCalendar date pickers open in.
languageNoLanguage for emails, Telegram messages and notification links.
expected_revNorev from preferences_get.
notificationsNoPer category channel switches (live categories only).
contact_channelNoPreferred way to be contacted; null clears it.
marketing_opt_outNoStop marketing messages.
reset_notificationsNoRestore default notification settings (needs confirm:true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing side effects and constraints: theme is persisted as the account default for future devices, notification rows only apply to live categories, and expected_rev provides optimistic-concurrency protection against overwriting a newer change. What it omits is what a successful call returns (e.g. a new rev to reuse), which matters for chained updates.

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 with the verb and the 'send only what changes' rule, then walks the fields in a single dense but scannable paragraph. No filler sentences, though the long run-on field list makes it slightly harder to parse than a bulleted layout would.

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?

With 9 optional parameters, no output schema, and supportive annotations, the definition covers every parameter, the confirm gate on reset, the concurrency token, and a hard capability limit. Nothing an agent needs to invoke it correctly is missing, aside from the shape of the return value.

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 the baseline is 3, but the description earns more by adding semantics the schema lacks: 'live categories' filtering for notifications, the null-clears-it behavior for contact_channel, and the conflict-avoidance purpose of expected_rev. Only the confirm/reset interaction is a restatement of what the schema already says.

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

Purpose4/5

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

Opens with a specific verb and resource ('Changes your own preferences') and immediately enumerates the mutable fields — language, theme, calendar, notifications, contact_channel, marketing_opt_out — so scope is unambiguous. The 'your own' qualifier separates it from company_update/profile_update, though it never names those siblings explicitly.

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

Usage Guidelines5/5

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

States the partial-update contract ('Send only what changes'), routes the agent to preferences_get for expected_rev, and gives an explicit exclusion: agreeing to marketing messages is not possible here. It also states the prerequisite pair reset_notifications + confirm:true, so no condition is left to inference.

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.

Resources