Skip to main content
Glama
Cyan Eclipse License Server

Cyan Eclipse License Server

Official

Issue a licence (execute proposal)

license_issue

Executes a confirmed proposal to mint a signed .cetlic licence, journaling issuance before release and returning the artefact, hash, and receipt.

Instructions

Execute an issue proposal and mint the licence: the signed .cetlic artefact is created and the issuance is written to the tenant journal BEFORE the artefact is returned (journal-before-release). Requires the proposal_id and the confirm token bound to its hash, plus a live mandate held by the caller covering the product and the issue operation class. Returns the licence id, the artefact string, its hash, the payload, and the journal receipt. A proposal executes exactly once. This is the only path that creates licences -- there is no unjournalled bulk issue.

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": {
      "proposal_id": "<proposal_id>",
      "confirm_token": "<confirm_token>",
      "_tenant_id": "<_tenant_id>",
      "_principal_id": "<_principal_id>"
    },
    "name": "license_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
_tenant_idYesTenant the call acts for. The tenant must exist; an unknown tenant is refused with state LICENSE_UNKNOWN. Transport authentication is a deployment concern -- this parameter scopes the call, it does not authenticate it.
proposal_idYesProposal id returned by the matching propose tool. The proposal must still be in proposed state and belong to the caller's tenant; anything else is refused and logged.
_principal_idYesActing principal inside the tenant. Principal-gated tools refuse unknown principals and principals of the wrong class; executions (tier T2) additionally require a live, unexpired mandate covering the product and the operation class.
confirm_tokenYesConfirm token bound to the proposal hash, in the shape confirm-<verb>-<proposal_id>-<first 12 of the proposal hash>. A token bound to any other proposal or hash is refused and logged; the token is the human-confirmation step of the propose -> confirm flow and is single-use.

Output Schema

NameRequiredDescriptionDefault
payloadNo
receiptNo
artefactNo
license_idNo
artefact_hashNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations it discloses ordering guarantees ('journal-before-release' -- the journal write happens before the artefact is returned), an exactly-once execution semantic ('A proposal executes exactly once'), and the authorisation requirement of a live mandate covering product and operation class. These are the operational facts an agent needs and none are derivable from readOnlyHint/openWorldHint/idempotentHint/destructiveHint.

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?

Three sentences, front-loaded with the action and its effects, then requirements, then the distinguishing constraint. No filler, and the most decision-relevant constraint is saved for last where it lands as a routing rule.

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

Completeness5/5

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

For a non-idempotent, mandate-gated mutation, the description covers effects, ordering, exactly-once behaviour, prerequisites and failure modes (unknown tenant -> LICENSE_UNKNOWN, stale proposal refused). An output schema exists, so the return-value list is redundant but harmless; nothing an agent needs in order to call it correctly is missing.

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 proposal_id, confirm_token, _tenant_id and _principal_id are already fully documented. The description restates the same requirements (proposal id, hash-bound token, mandate) and adds only the framing that the token is the human-confirmation step, so the baseline 3 applies.

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 description opens with a specific verb and resource ('Execute an issue proposal and mint the licence') and spells out the concrete effects: a signed .cetlic artefact is created and the issuance is journalled. The closing sentence 'This is the only path that creates licences -- there is no unjournalled bulk issue' separates it from the propose/list/inspect siblings without the agent needing to open 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 states the preconditions for calling it (proposal_id, a confirm token bound to the proposal hash, and a live mandate covering the product and issue operation class) and rules out alternative paths with 'the only path that creates licences'. What it doesn't do explicitly is name license_issue_propose as the step that must precede it, leaving the propose -> confirm flow to be inferred from the parameter description.

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