Skip to main content
Glama
SunLicense MCP server

SunLicense MCP server

Official

create_policy

Create a product license policy (plan or tier) with type, machine/IP limits, and duration so licenses can be issued from it.

Instructions

Create a policy for a product: a plan or tier customers buy (e.g. Pro, Lite, Trial), i.e. the license template with its type, machine limit, IP limit and duration. Licenses are issued from policies (issue_license). maxMachines, maxIps or durationDays left out means unlimited.

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": {
      "product": "<product>",
      "name": "<name>"
    },
    "name": "create_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesthe plan or tier's name, e.g. 'Pro' or 'Trial'
typeNoPERPETUAL (never expires), SUBSCRIPTION (expires durationDays after issue) or TRIAL (a time-boxed evaluation). Default: SUBSCRIPTION with durationDays, else PERPETUAL
maxIpsNoIP addresses one license may be used from (e.g. 1 for one server; IPv6 counts per /64); unlimited when left out
productYesproduct id, code or name
maxMachinesNomachines one license may run on at once; unlimited when left out
durationDaysNodays a license lasts after issue; needed for SUBSCRIPTION and TRIAL

Output Schema

NameRequiredDescriptionDefault
createdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the policy is a license template with type/machine/IP limits and duration, and omitted limit fields mean unlimited rather than zero. It does not cover duplicate-name behavior, whether the product must already exist, or permission requirements.

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?

Two dense but well-ordered sentences: the identity of the object comes first, the relationship to issue_license second, and the omission semantics last. Every clause carries information and there is 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 an output schema present, return values need not be described, and all six parameters are fully specified between schema and description. What remains unstated is failure/edge behavior such as duplicate policy names or a nonexistent product, which matters somewhat for a non-idempotent create.

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 including the type enum and the unlimited-when-omitted semantics is already documented in the schema. The description's note that "maxMachines, maxIps or durationDays left out means unlimited" largely restates what the schema fields say, so it adds only modest reinforcement rather than new meaning.

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?

Uses a specific verb and resource ("Create a policy for a product") and immediately defines the domain concept as "a plan or tier customers buy (e.g. Pro, Lite, Trial)", i.e. the license template. It also draws the boundary against issue_license by noting licenses are issued from policies, so an agent can distinguish it from the sibling that consumes policies.

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 establishes the ordering relationship with issue_license (create the policy first, then issue licenses), which is the key usage context. It does not explicitly address when to use update_policy or list_policies instead, but for a create operation the intended context is unambiguous.

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