Skip to main content
Glama

Set notifications

set_notifications
DestructiveIdempotent

Change how the person is told about Offers and checks. Leave out request_id to change their account-wide settings. check_frequency: adaptive, weekly, monthly or never. check_channels: agent_then_email (email after 24 hours unanswered), agent_only or email_only.

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": "set_notifications"
  }
}

Input Schema

NameRequiredDescriptionDefault
request_idNoThe Request’s id from list_requests.
request_keyNoOptional. The same key repeats a change safely; one is derived when left out.
offer_alertsNoWhether the person is emailed new Offers.
check_channelsNoWho asks: you, then email; only you; or only email.
check_frequencyNoHow often the person is asked if they still want it.
agent_reachabilityNoTurn email or polling on or off for this Request.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds meaningful channel behavior (email fires after 24 hours unanswered) but never acknowledges that turning channels/alerts off is a consequential change, nor mentions permissions or reversibility. Given the destructive annotation, the description should have flagged what gets suppressed.

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?

Compact and front-loaded: scope rule first, then per-parameter semantics. No filler sentences, though the opening clause "told about Offers and checks" is slightly awkward prose that could be tighter.

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

Completeness3/5

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

An output schema exists and the input schema documents all six parameters, so return values and most param semantics are covered elsewhere. What remains missing is behavioral context for a destructive mutation: effect of disabling alerts/channels, permission prerequisites, and interaction with agent_reachability.

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, but the description genuinely adds meaning: it lists the allowed check_frequency values and expands check_channels beyond the schema with "email after 24 hours unanswered," which is operational detail the schema lacks. It also explains the request_id omission semantics at the tool level.

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?

States a specific verb ("Change") and a concrete resource (how the person is told about Offers and checks), which is clearly distinct from siblings like respond_to_offer or close_request. It does not explicitly name an alternative notification tool, but the scope is unambiguous.

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

Usage Guidelines3/5

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

The line "Leave out request_id to change their account-wide settings" gives a useful conditional rule for selecting request-scoped versus account-wide behavior. It stops short of stating when to prefer this over sibling tools or any preconditions (e.g., ownership/permission requirements), so guidance is implied rather than complete.

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