Skip to main content
Glama

Set cost budget

set_cost_budget
Destructive

Create a monthly cost budget, or change one. To create, give name, scope_kind (organisation, project, cluster, environment or application), scope_id (the project, cluster or application id, or the environment label; omit for the organisation), monthly_amount in whole units of currency, and currency; a scope holds one budget. To change, give budget_id and only the fields that change - the scope never changes, the rest keeps its value, and owner_user_id null or clear_owner true clears the owner. notify_at_pct (default 80) is the share of the budget at which its card is raised. Organisation admins only (billing.manage); every change is audited. Reversible by setting the previous values back (read get_cost_budgets 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": "set_cost_budget"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo1 to 120 characters.
currencyNousd, eur, gbp, sek, nok, dkk, chf, pln, czk, jpy, cad, aud or inr.
scope_idNoThe project, cluster or application id, or the environment label; omit for the organisation. Only on a create.
budget_idNoThe budget to change; omit to create one.
scope_kindNoWhat the budget covers; only on a create. A project budget covers the clusters the project holds now.
clear_ownerNoClear the owner on a change.
notify_at_pctNoRaise the budget's card when the projection reaches this percent of the budget. Defaults to 80 on a create.
owner_user_idNoAn active member of the organisation the budget is for; null clears.
monthly_amountNoThe budget per month in whole units of currency, like 5000 for 5,000 EUR.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / scope_id / description
      Previous value: -"The cluster or application id, or the environment label; omit for the organisation. Only on a create."New value: +"The project, cluster or application id, or the environment label; omit for the organisation. Only on a create."
    • changedInput schema / properties / scope_kind / description
      Previous value: -"What the budget covers; only on a create."New value: +"What the budget covers; only on a create. A project budget covers the clusters the project holds now."
    • changedInput schema / properties / scope_kind / enum
      Previous value: -[
      -  "organisation",
      -  "cluster",
      -  "environment",
      -  "application"
      -]New value: +[
      +  "organisation",
      +  "project",
      +  "cluster",
      +  "environment",
      +  "application"
      +]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say non-read-only, non-idempotent, destructive; the description adds the authorization gate ("Organisation admins only (billing.manage)"), the auditing guarantee, the immutability of scope on change, the field-retention rule, and how to clear an owner. It also clarifies that despite destructiveHint the change is reversible by restoring prior values — nuance, not contradiction.

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 front-loaded with the create/change distinction and every clause carries information, but the second half becomes a dense run-on separated only by semicolons and dashes, which slows parsing of the change-mode rules.

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?

For a 9-parameter, dual-mode, permissioned mutation tool with no output schema, the definition covers modes, constraints, auth, audit and reversibility. The only omission is what the tool returns on success, which the agent must infer.

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 already 100%, so the baseline is 3, but the description adds real meaning: create-only vs change-only parameters, that scope_id is omitted for organisation scope, that notify_at_pct defaults to 80 on create, and that owner_user_id null / clear_owner true clears the owner. It does not restate currency or unit formats beyond the schema, which is correct restraint.

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?

"Create a monthly cost budget, or change one" names the resource (monthly cost budget) and both verbs the tool performs, which is exactly what an agent needs to distinguish it from get_cost_budgets, delete_cost_budget and the cost-decision siblings. The scope is further pinned down by the one-budget-per-scope rule.

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?

It explicitly splits the two modes: "To create, give ..." and "To change, give budget_id and only the fields that change". It also prescribes a prerequisite read ("read get_cost_budgets first" for reversibility), which routes the agent to the correct sibling before mutating.

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.