Help by DeltaBreen

create_button

Add a button beside the ticket that asks the integration's URL to do something to the customer's account. The URL receives type "action" with the button's key, and must do the work and answer {"ok": true}. Owner only, on a plan with buttons.

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": {
      "integration_id": "<integration_id>",
      "label": "<label>"
    },
    "name": "create_button"
  }
}

Input Schema

Name	Required	Description
`label`	Yes	The words on the button, like "Cancel subscription". Up to 40 characters. The URL receives a key made from it (cancel_subscription).
`extra_fields`	No	Things to fill in before pressing, like a reason or an amount. Up to 10.
`word_to_type`	No	The word a person types before the button runs. The default is "confirm".
`who_can_press`	No	Who may press it besides the owner: any of "admin" and "agent". The default is both.
`integration_id`	Yes	The integration the button belongs to (a uuid from list_integrations).
`cannot_be_undone`	No	true if what it does cannot be undone: the button is shown in red with a warning.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 27, 2026

changedInput schema / $defs / ExtraField / properties / options / type
```
Previous value: -[
-  "array",
-  "null"
-]New value: +"array"
```
changedInput schema / $defs / ExtraField / properties / required / type
```
Previous value: -[
-  "boolean",
-  "null"
-]New value: +"boolean"
```

changedInput schema / $defs / ExtraField / properties / type / type

Previous value: -[
-  "string",
-  "null"
-]New value: +"string"

changedInput schema / properties / cannot_be_undone / type

Previous value: -[
-  "boolean",
-  "null"
-]New value: +"boolean"

changedInput schema / properties / extra_fields / type

Previous value: -[
-  "array",
-  "null"
-]New value: +"array"

changedInput schema / properties / who_can_press / type

Previous value: -[
-  "array",
-  "null"
-]New value: +"array"

changedInput schema / properties / word_to_type / type

Previous value: -[
-  "string",
-  "null"
-]New value: +"string"

First observedOct 27, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Beyond the annotations (which only declare this is a non-read-only, non-idempotent write), the description explains the runtime contract of the artifact being created: the integration URL receives type "action" with the derived key and must respond {"ok": true}, plus the owner-only permission requirement. It omits what the call itself returns and whether button keys must be unique, so it is not exhaustive.

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?

Roughly three short sentences with the core action and the callback protocol front-loaded, and prerequisites at the end. Dense but every clause carries information; no filler.

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?

With six fully documented parameters, annotations covering the safety profile, and no output schema, the description is nearly sufficient. The main remaining gap is that nothing says what the tool returns (e.g., a button id) for later update_button/press_button calls.

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 description coverage is 100%, so every parameter is already documented in the input schema down to the label-to-key derivation. The description adds no parameter-level meaning beyond restating that the URL receives the key. Baseline 3 applies when the schema carries the burden.

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?

The description opens with a specific verb+resource ("Add a button beside the ticket") and immediately explains the mechanism (integration URL invoked with type "action"). This naturally separates it from list_buttons, update_button, remove_button and press_button, though it never names any of them explicitly.

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?

It gives concrete preconditions: "Owner only, on a plan with buttons." That tells the agent when the call will legitimately succeed. It does not state any exclusions or point at alternatives such as update_button or press_button, so it stops short of a 5.

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

All Help by DeltaBreen 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?