All's Well

Create Notification Contact Tool

create-notification-contact

Create a notification contact (an alert destination). config holds the keys its type needs: {"email": "ops@example.com"} for email; {"webhook_url": "https://hooks.slack.com/..."} for slack or discord; {"url": "https://..."} for webhook; {"bot_token": "...", "chat_id": "-100123"} for telegram. Other keys are dropped.

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": {
      "name": "<name>",
      "type": "<type>",
      "config": "<config>"
    },
    "name": "create-notification-contact"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Contact name.
`type`	Yes	Delivery channel.
`config`	Yes	The keys this type needs (see the tool description).
`notify_on_down`	No	Alert when a monitor goes down (default true).
`notify_on_recovery`	No	Alert when a monitor recovers (default true).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations carry only a title, so the description bears the full behavioral burden. It does add one genuinely useful trait — 'Other keys are dropped' tells the agent that malformed config is silently trimmed rather than erroring. It says nothing about permissions, duplicate-name behavior, whether alerts fire immediately, or what is returned.

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?

Purpose first, then the conditional config contract, then the silent-drop caveat. Every clause earns its place and there is no filler; the dense per-type listing is the right form for enumerating five channel variants.

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 create tool with no output schema, the description nails the hardest part (nested, type-dependent config) and flags the silent key-dropping behavior. The remaining gap is minor: it never says what is returned or how the new contact is identified, which an agent would need to chain into a follow-up call.

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 adds the conditional type-to-config mapping that the flat schema cannot express — which keys each enum value requires, with concrete examples per channel. That is meaningfully beyond what a per-property description conveys.

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 and resource ('Create a notification contact') and glosses it for readers unfamiliar with the vocabulary ('an alert destination'). It is distinguishable from list-notification-contacts, but the differentiation comes from the create/list verb rather than any explicit sibling reference.

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 creation context is implied by 'Create', but there is no guidance on prerequisites (e.g., does a channel need verification), on what to do if a contact with the same name exists, or on which sibling to consult first to inspect existing contacts. Adequate but leaves the agent to infer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All All's Well tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?