Skip to main content
Glama

Propose cluster access policy

propose_cluster_access_policy
Destructive

Propose a change to the organisation cluster access policy (the twin of ankra org access-policy set). This never changes the policy: no token may. It records a proposal and returns its apply_url; an organisation owner or admin must open that link while signed in to the Ankra web app and apply it. Give the user the link and say so. Omitted fields keep their current value; elevated_max_ttl_seconds and require_reason_from_role may be null to clear the bound. A new proposal replaces a pending one; proposals expire after 7 days, and applying fails if the policy changed in the meantime. reason is required. The result names organisation_id and organisation_name, the organisation the proposal was recorded in. Requires kube_access.manage.

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": {
      "reason": "<reason>"
    },
    "name": "propose_cluster_access_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy the policy should change. The owner or admin who applies the proposal reads it.
max_grant_roleNoHighest role any cluster access grant in the organisation may carry.
creator_grant_roleNoRole the user who creates or imports a cluster receives on it; none seeds no grant. Must not exceed max_grant_role, and must be view or none while elevated_max_ttl_seconds is set.
elevated_max_ttl_secondsNoLongest a grant above view may last, in seconds (60 to 31536000); null removes the bound.
require_reason_from_roleNoLowest role whose grants must carry a reason: view, edit, admin or cluster-admin; null removes the bound.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Goes well beyond the annotations, disclosing that no token can mutate the policy directly, that a new proposal replaces a pending one, that proposals expire after 7 days, that apply fails on concurrent policy change, and that kube_access.manage is required. The destructiveHint=true is consistent with replacing a pending proposal. If anything it could state more explicitly that the prior pending proposal is discarded, but the behavioral picture is strong.

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?

Dense but front-loaded: the no-mutation guarantee and the apply-link obligation come first, with edge cases after. Every sentence carries information, though the parenthetical CLI twin reference and the 'Give the user the link and say so' instruction add instruction-style verbosity rather than tool semantics.

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?

Covers permissions, lifecycle (expiry, replacement, conflict-on-apply) and names the returned fields (apply_url, organisation_id, organisation_name) despite no output schema. A delegation-style workflow tool is well served; only a pre-flight recommendation to read the current policy 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 coverage is 100%, so the baseline is 3. The description adds real meaning on top: omitted fields keep current values, and the two nullable fields clear the bound when null, plus 'reason is required'. However the per-field role-constraint relationships are already carried by the schema text.

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?

States a specific verb and resource ('Propose a change to the organisation cluster access policy') and immediately frames the scope: it records a proposal rather than mutating state, and names the exact counterpart command. This clearly separates it from get_cluster_access_policy and the set_* siblings.

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?

Explains the required follow-through precisely: the agent must hand the returned apply_url to a user, and an owner/admin must open it signed in to apply. It does not explicitly route to a reading sibling (e.g. get_cluster_access_policy to inspect the current policy first), so usage is clear but not fully comparative.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.