Create failure alerts that fire when a job dead-letters and send notifications via email, webhook, or Slack.
Create a failure alert. Fires when a job dead-letters. Channel is email, webhook, or slack.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| jobId | No | Scope to one job; omit for all jobs | |
| target | Yes | Email address, webhook URL, or Slack webhook URL | |
| channel | Yes | ||
| enabled | No | ||
| cooldownMinutes | No | ||
| consecutiveFailuresThreshold | No |
Changes observed during successful MCP inspections.
v0.1.10Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the trigger semantics (dead-letter) and the delivery channels, but says nothing about side effects, required permissions, whether alerts start enabled, what happens on duplicate names, or how consecutiveFailuresThreshold and cooldownMinutes change firing behavior. Too much of a mutation tool's behavior is left unstated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short, front-loaded sentences with the core action first and no filler. Slightly reduced because the channel enumeration duplicates the schema enum rather than adding information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 7-parameter mutation tool with no annotations, no output schema, and sparse schema descriptions, the definition is under-built. However, the trigger context it does give (dead-letter alerts, three channels) is the piece the schema could not convey, so it is not wholly inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 29%, so the description must compensate and does not: enabled, cooldownMinutes, and consecutiveFailuresThreshold are undocumented anywhere. 'Channel is email, webhook, or slack' merely restates the enum, and the channel-to-target format mapping is already in the target property description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb and resource ('Create a failure alert') plus the trigger condition ('fires when a job dead-letters'), which tells the agent this is a notification-config tool rather than a job-mutating one. It does not explicitly contrast with update_alert or get_alert, but the create/list/update/delete family makes the distinction largely self-evident.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The dead-letter trigger implies when this tool is relevant, but the description never states prerequisites (does the job need to exist? must jobId be supplied for a job-scoped alert?), nor when to choose create_alert over update_alert, or how to verify an alert exists first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.