Skip to main content
Glama
Featureflip

Featureflip

Official

Create, edit, end, or delete a change freeze

manage_change_freeze
Destructive

Create, schedule, and end change freeze windows, then approve or revoke scheduled changes that need to apply during a freeze.

Instructions

Manage change freeze windows. action=create makes a window: name + reason + environments (keys) or all_environments. Give starts_at and ends_at to schedule it; omit starts_at to start at once, and omit ends_at for an open-ended freeze (a scheduled window with starts_at needs ends_at). action=freeze_now starts at once and never takes starts_at; it may leave ends_at open until you end it. Pass project for a project window; omit it for an organization-wide one. scheduled_change_policy: Hold (default) keeps scheduled changes pending until the freeze ends, Fail fails them. action=update needs freeze_id and changes only the fields you pass (accepts ifMatch). action=end stops an active window now. action=delete removes an UPCOMING window. action=approve_scheduled_change (freeze_id + scheduled_change_id + reason) lets one pending scheduled change apply inside the freeze; revoke_approval withdraws it. Creating a window or approving a change needs the Business plan or above (below it, update can only rename, change the reason or shorten); ending, deleting and revoking work on any plan. All need an Admin token.

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": {
      "action": "<action>"
    },
    "name": "manage_change_freeze"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoWindow name, e.g. "Black Friday code freeze"
actionYescreate and freeze_now need name + reason + environments or all_environments; update, end and delete need freeze_id; approve_scheduled_change needs freeze_id + scheduled_change_id + reason; revoke_approval needs freeze_id + scheduled_change_id
reasonNoWhy the freeze exists (shown to people it blocks); for approve_scheduled_change, why the change may proceed
ends_atNoISO 8601 UTC end. On create: required when scheduling (with starts_at); omitting it with no starts_at makes an open-ended freeze. On update: omitting it leaves the end unchanged.
ifMatchNoetag from list_change_freezes with freeze_id. The write is refused with 412 if the resource changed since that read; re-read and re-apply. Omit to write unconditionally.
projectNoProject key for a project window; omit for organization-wide
freeze_idNoFreeze id (see list_change_freezes)
starts_atNoISO 8601 UTC start. create only: omit (or use freeze_now) to freeze immediately
environmentsNoEnvironment keys the window covers, e.g. ["production"]
idempotency_keyNoIdempotency-Key (a UUID) for create, freeze_now, end and approve_scheduled_change
all_environmentsNoCover every environment instead of listing them
scheduled_change_idNoScheduled change id, for approve_scheduled_change and revoke_approval
scheduled_change_policyNoWhat happens to scheduled changes that come due inside the window (default Hold)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.11.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only carry destructiveHint=true, and the description adds substantial context beyond it: plan-tier limits per action, Admin token requirement, the constraint that delete only removes an UPCOMING window, that update is a partial write accepting ifMatch, and the conditional rule that a scheduled window with starts_at needs ends_at. The ifMatch/412 re-read-and-reapply behavior and idempotency usage are also disclosed.

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?

It is a dense but front-loaded run of action-by-action clauses with no filler, and every sentence carries an operational rule. The trade-off is that seven actions are packed into prose rather than a scannable list, which makes it slightly harder to locate a single action's rules quickly.

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 13-parameter, seven-action mutation tool this covers what an agent needs: which parameters each action requires, plan and auth prerequisites, destructive scope of end and delete, concurrency via ifMatch, and idempotency. Return values need not be explained because an output schema exists.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents each parameter's type and meaning, and the description partly repeats it (ends_at scheduling rules, project omission). It still adds cross-parameter conditional logic the schema doesn't state on its own, such as freeze_now never taking starts_at and the create/freeze_now vs update/end/delete parameter bundles.

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+resource ("Manage change freeze windows") and then enumerates all seven actions with their effects: create makes a window, freeze_now starts immediately, update changes only passed fields, end stops an active window, delete removes an UPCOMING window, approve/revoke act on a single scheduled change. This lets an agent distinguish this multi-action tool from siblings like list_change_freezes, which it explicitly points to for ids.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Selection logic between the actions is spelled out: use create vs freeze_now, omit starts_at to start at once, omit ends_at for an open-ended freeze, pass project for a project window vs omitting it for org-wide, and Hold vs Fail for scheduled_change_policy. It also states plan gating conditions (create and approve need Business+, end/delete/revoke work on any plan) and the Admin token requirement.

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