Skip to main content
Glama

Heartbeat — dead-man switch for cron jobs & AI agents

by io.github.aniripsaretro-max

create_heartbeat

Arm a new dead-man switch monitor. Returns the key plus a ping_url your job must hit after every run. No account needed. Names are globally unique on this instance and each name gets a PUBLIC status page; the secret key is the only credential — keep it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNopush = you ping us; pull = we probe target_url every min(period_s,60)s; selfcheck = your box runs our egress-trust probe script and POSTs verdict reports to the ping URLpush
nameYesunique name, 1-40 chars [A-Za-z0-9_.-]
grace_sNoextra seconds of slack before DOWN (0-86400)
pass_keyNoPro pass key from a $5 USDC payment (optional; skips rate limits)
period_sNoexpected seconds between pings (60-86400)
depends_onNoparent monitor names and/or gate:<gate-name> entries (max 5). When a parent is DOWN or a gate parent is HALT this monitor becomes DEGRADED-BY-UPSTREAM: notified once, own silence paging suppressed until the parent recovers.
target_urlNopublic http(s) URL to probe (pull only)
webhook_urlNopublic http(s) URL that receives UP/DOWN alerts (optional)

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden. It discloses key traits: names are globally unique, each name gets a PUBLIC status page, no account is needed, and the secret key is the only credential. It does not cover rate limits or duplicate-name behavior, but the security and privacy implications are well addressed.

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

Conciseness5/5

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

Three concise sentences, each earning its place: what the tool does, what the caller receives, and the important security/uniqueness context. The most critical information is front-loaded.

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?

The description covers the essential return values (key, ping_url) and auth context (no account, secret key only), while the schema covers parameters. It does not specify the exact response structure or failure modes, but for a create tool with a rich schema this is reasonably complete.

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?

The schema already documents all 8 parameters with 100% coverage, so the description need not repeat parameter details. The description adds context about global uniqueness and the returned key, but it does not meaningfully explain parameter behavior beyond what the schema provides. 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?

The description starts with a specific action, 'Arm a new dead-man switch monitor,' and clearly states what the tool creates and returns: a key and a ping_url. This distinguishes it from siblings like get_status, list_heartbeats, ping_heartbeat, and record_failure, which operate on existing monitors rather than creating them.

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 description implies the tool is for setting up a new monitor and says the returned ping_url must be hit after each run, but it never explicitly contrasts with ping_heartbeat or states when not to use this tool. No account needed' gives some context, but alternative routing 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.

All Heartbeat — dead-man switch for cron jobs & AI agents 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

A4.3/5.0
Disambiguation5/5

Each tool maps to a distinct action: creating a monitor, checking one monitor's full state, listing monitors, signaling success, and recording failure. get_status and list_heartbeats are the closest pair, but their cardinality and detail level make them easy to tell apart.

Naming Consistency5/5

All tool names use lowercase snake_case with a clear verb-first pattern: create, get, list, ping, record. The nouns are all meaningful in the heartbeat domain, and there is no mixing of camelCase or vague verbs like 'process' or 'run'.

Tool Count5/5

Five tools is well-scoped for a focused dead-man switch service. Each tool covers a necessary part of the workflow without redundancy or bloat.

Completeness3/5

The core loop is covered: create a monitor, ping success, record failure, and inspect status. However, there is no update, delete, or disarm tool, so changing monitor configuration or retiring a job leaves an active monitor that will eventually go down and alert.

Resources