Skip to main content
Glama
MCP Connect Starter

MCP Connect Starter

by cdtalley

add_ticket_comment

Add a comment to a ticket and return the updated ticket. This write operation is disabled by default and requires the crm:write scope.

Instructions

Add a comment to a ticket and return it updated.

Disabled by default (see config/scopes.yaml) -- this is the one write-capable tool in the starter, gated behind the crm:write scope to demonstrate least-privilege-by-default.

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": {
      "ticket_id": "<ticket_id>",
      "author": "<author>",
      "body": "<body>"
    },
    "name": "add_ticket_comment"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
authorYes
ticket_idYes

Output Schema

NameRequiredDescriptionDefault
idYes
statusYes
subjectYes
assigneeNo
commentsNo
priorityYes
created_atYes
updated_atYes
descriptionYes
requester_emailYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied the description carries the full burden, and it does disclose the key traits: this is a mutation, it is off unless the `crm:write` scope is granted, and it returns the updated ticket. It stops short of stating failure modes (unknown ticket_id, scope rejection error shape) or whether the comment is appended vs. replaces anything.

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?

The core action is front-loaded in one tight sentence, with the gating caveat second. The trailing rationale ('to demonstrate least-privilege-by-default') is explanatory framing rather than operational detail, slightly diluting an otherwise efficient definition.

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

Completeness3/5

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

The output schema means return values need no prose, and the scope warning covers the main behavioral risk for a simple 3-parameter write. What remains missing is exactly the part structured data doesn't supply: meaning for `author` and `body`, and expected behavior on an invalid ticket_id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three required parameters, so the description must compensate and does not. It implies ticket_id and body through 'add a comment to a ticket' but never mentions the `author` parameter or any format/constraint for any of the three.

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 first sentence gives a precise verb and resource ('Add a comment to a ticket') plus a side effect ('return it updated'), and the second sentence distinguishes it from every sibling by declaring it 'the one write-capable tool in the starter'. An agent can separate it from get_ticket/list_tickets without inspecting any schema.

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 clearly states the operational precondition: disabled by default, enabled only with the `crm:write` scope, which tells the agent to expect authorization failures otherwise. It does not describe a when-not-to-use case, but no sibling offers an alternative comment path, so the omission is minor.

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