Skip to main content
Glama

Remix an alarm

remix_alarm

Makes the person their own copy of someone else's alarm (a remix): it keeps the original's history, state, rule and sources (shared, nothing is crawled twice), and adds the pages the person wants watched as well, under their own rule. For "I like this alarm but also watch X" or a rule that needs something the original does not watch (set_stack_trigger says so). Only a public monitoring alarm can be remixed: a token, a wallet, an account or a channel. Events and time alarms are their Keeper's own.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "link": "<link>",
      "want": "<want>"
    },
    "name": "remix_alarm"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkYesThe original alarm's link (lfg.gm/a/...), the message it came in, or its code.
ruleNoThe rule it rings on, in plain words. Left out, the original's rule comes along.
wantYesWhat the copy is for, in the person's words.
titleNoWhat the copy says when it rings. Left out, the original's name plus "remix".
add_sourcesNoPages to watch as well.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / properties / place
      Removed value: -{
      -  "description": "A sun alarm's copy only: where it rings, \"Lisbon\". Needed for a sun alarm.",
      -  "maxLength": 200,
      -  "minLength": 2,
      -  "type": "string"
      -}
    • removedInput schema / properties / song
      Removed value: -{
      -  "description": "A sun alarm's copy only: the feel of the song to ring with, \"calm piano\", or \"same\" to keep the original's.",
      -  "maxLength": 80,
      -  "minLength": 2,
      -  "type": "string"
      -}
  2. Changed2 schema fields changed
    • addedInput schema / properties / place
      Added value: +{
      +  "description": "A sun alarm's copy only: where it rings, \"Lisbon\". Needed for a sun alarm.",
      +  "maxLength": 200,
      +  "minLength": 2,
      +  "type": "string"
      +}
    • addedInput schema / properties / song
      Added value: +{
      +  "description": "A sun alarm's copy only: the feel of the song to ring with, \"calm piano\", or \"same\" to keep the original's.",
      +  "maxLength": 80,
      +  "minLength": 2,
      +  "type": "string"
      +}
  3. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare it is a non-destructive, non-idempotent, open-world write. The description adds real behavioral substance beyond that: sources are shared so "nothing is crawled twice," the original's history and state carry over, and eligibility is limited to public monitoring alarms. It does not address what happens on repeated calls (non-idempotent) or what the caller gets back, leaving some annotation-covered behavior unelaborated.

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?

Four sentences, front-loaded with the core action and its copy semantics before the qualifying scenarios and restrictions. Slightly dense with parenthetical asides, but every sentence carries distinguishing information rather than restating the name.

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

Completeness4/5

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

For a 5-parameter mutation tool with no output schema, the description covers eligibility, what gets carried over, and how new sources combine with the original rule. What remains unstated is the return value (presumably a new alarm reference) and whether the source alarm is affected — minor but non-trivial omissions.

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 coverage is 100%, including defaults for rule and title, so the schema already carries the parameter semantics. The description adds only the conceptual point that added sources run "under their own rule" and that link may be a link, the message it came in, or a code — marginal value over the schema, so baseline 3 applies.

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?

States a concrete verb and resource ("Makes the person their own copy of someone else's alarm") and immediately clarifies what "remix" means: shared history, state, rule and sources plus added pages. It distinguishes itself from create-style siblings by framing the copy as derived from an existing public alarm.

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 explicit trigger scenarios ("I like this alarm but also watch X" or a rule needing something the original does not watch) and explicit exclusions: only public monitoring alarms (token, wallet, account, channel); events and time alarms are "their Keeper's own." The gap is that it never contrasts with the closely-related join_alarm or heart_alarm siblings, so an agent must infer remix vs. join from the word "own copy."

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.