Skip to main content
Glama
Sign In
On Board

On Board

by swisspra
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_create_ticket

Create a help ticket for another agent, assign it to a specific agent or leave it open in the shared queue so work can be picked up and continued.

Instructions

Create a ticket requesting help from another agent.

Ticket is saved as .md file in tickets/ (open queue). Assign to a specific agent NAME or leave open for anyone.

Examples:

  • PM needs coder: assigned_to="cursor-coder"

  • Coder needs review: assigned_to="codex-main"

  • Anyone can pick up: assigned_to=None

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": {
      "params": "<params>"
    },
    "name": "memory_create_ticket"
  }
}

Input Schema

NameRequiredDescriptionDefault
paramsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.2.0
    • changedInput schema / $defs / CreateTicketInput / properties / assigned_to / description
      Previous value: -"Agent name or platform to assign (e.g. 'cursor', 'codex'). Empty = any agent."New value: +"Stable agent name to assign (e.g. 'cursor-coder', 'codex-main'). Exact, case-sensitive match — a platform name is not an assignee. Empty = any agent."
  2. First observedv4.0.4

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the mutation profile is covered. The description adds real context beyond that — the ticket lands as a .md file in tickets/ as an open queue item — but says nothing about what happens on duplicate titles, whether the ticket must later be claimed/submitted, or any authorization requirement.

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?

Two sentences plus three short examples: the purpose is front-loaded and the bullets are scannable. The examples partly duplicate the assigned_to property description, so there is minor redundancy, but nothing is padded.

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?

An output schema exists, so return values need not be explained, and the inner CreateTicketInput fields (scope, forbidden, required_fields, target_url) are self-documented in the schema. Still, for a 12-field creation tool whose top-level 'params' is undocumented, the description should at least say the single params object must satisfy CreateTicketInput; that gap keeps it at merely adequate.

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 reported at 0% because the single top-level 'params' wrapper is undocumented, and the description does nothing to explain that wrapper or the CreateTicketInput structure it must contain. The assignment examples restate what the nested assigned_to property already documents (stable agent name, e.g. 'cursor-coder'), so the description adds little beyond the inner schema.

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 ticket requesting help from another agent', with the extra qualifier that it goes into the open queue in tickets/. That is enough to distinguish it from memory_claim_ticket / memory_submit_ticket behaviorally, but the description never names those siblings or explains the queue lifecycle, so an agent still has to infer the ordering from the tool names alone.

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 three worked examples show the intended assignment routing (assigned_to a specific agent vs. None for anyone), which implies when to use the tool. However, there is no explicit statement of when to create a ticket versus memory_write, memory_handoff, or the ticket siblings, and no prerequisites or exclusions are given.

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

Deploy Server

Other Tools