Skip to main content
Glama

Update cost autopilot

update_cost_autopilot
Destructive

Change the organisation's cost autopilot policy, one project's defaults layer, or one cluster's tier - one of the three per call. For a project, give project_id with defaults (the project's clusters take those tiers over the organisation's, under any cluster override) or clear_project_defaults true. For the policy, name only what changes: defaults maps the environment kinds to change to tiers (kinds left out keep theirs), quiet_hours and notification_route_id are set or cleared with null (the route is kept with the policy; no notice is sent to it today). For one cluster, give cluster_id with a tier and the reason its cards will show (optionally expires_at), or clear_override true to return it to its environment's tier. Needs billing.manage and clusters.write; every change is audited, and the savings cards carry the new tier from their next read. Reversible by setting the previous values back (read get_cost_autopilot first).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "update_cost_autopilot"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoThe tier to put the cluster in.
reasonNoWhy, as the cluster's cards will show it: 3 to 500 characters.
defaultsNoEnvironment kinds to change and their tiers.
cluster_idNoThe cluster whose tier to set or clear, from get_cost_autopilot.
expires_atNoRFC 3339 time the override stops applying; omit for never.
project_idNoUUID of a project whose defaults layer to set (with defaults) or clear (with clear_project_defaults). The project's clusters take these tiers over the organisation's defaults, under any cluster override. list_projects has the ids.
quiet_hoursNoWhen the autopilot starts no change of its own; null clears.
clear_overrideNoReturn the cluster to its environment's tier.
notification_route_idNoA notification route of the organisation to keep with the policy (no notice is sent to it today); null clears.
clear_project_defaultsNoWith project_id: remove the project's defaults so its clusters follow the organisation's again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / notification_route_id / description
      Previous value: -"A notification route of the organisation for the autopilot's pre-notices; null clears."New value: +"A notification route of the organisation to keep with the policy (no notice is sent to it today); null clears."
  2. Changed2 schema fields changed
    • addedInput schema / properties / clear_project_defaults
      Added value: +{
      +  "description": "With project_id: remove the project's defaults so its clusters follow the organisation's again.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / project_id
      Added value: +{
      +  "description": "UUID of a project whose defaults layer to set (with defaults) or clear (with clear_project_defaults). The project's clusters take these tiers over the organisation's defaults, under any cluster override. list_projects has the ids.",
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag a destructive, non-idempotent write, and the description adds real depth beyond them: required scopes (billing.manage, clusters.write), audit logging, the read-after-write propagation detail ('savings cards carry the new tier from their next read'), the side-effect caveat that a notification_route_id is retained but no notice is sent, and an explicit reversal recipe. The interaction between project defaults, environment tier, and cluster override is also explained as a precedence rule.

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?

Front-loaded with the one-of-three constraint before the per-mode detail, which is the right ordering for an agent. The body is a single dense paragraph of long clauses, so mode boundaries are slightly harder to scan than a bulleted or numbered layout would be, but every sentence carries operational information and there is no filler.

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 10-parameter tool with nested objects, zero required parameters, and no output schema, the description supplies everything needed to invoke it correctly: mode selection, required scopes, precedence rules, side effects, reversibility, and read-before-write. The absence of an output schema is not a gap because the description notes where to read current state (get_cost_autopilot).

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 baseline is 3, but the description goes further by explaining merge semantics that the schema cannot express: 'defaults maps the environment kinds to change to tiers (kinds left out keep theirs)' and the null-clears-versus-omitted distinction for quiet_hours and notification_route_id. It also documents the precedence layering (project defaults above org defaults, below cluster override) and the reason length expectation, though it does not restate the tier enum values.

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?

Opens with a specific verb and resource ('Change the organisation's cost autopilot policy, one project's defaults layer, or one cluster's tier') and immediately bounds the scope with 'one of the three per call'. The three-way targeting (org policy / project defaults / cluster override) is spelled out so an agent can distinguish it from get_cost_autopilot and other update_* siblings.

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?

Gives explicit selection rules for each of the three modes, including the exact argument combination that selects each (project_id + defaults vs. clear_project_defaults; cluster_id + tier + reason vs. clear_override). It also states the ordering prerequisite 'read get_cost_autopilot first' and the partial-update rule 'name only what changes', so nothing is left to inference.

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.