Skip to main content
Glama

Apply an approved proposal

apply_changes
Destructive

Apply one or more user-approved proposals to an account atomically; roll back all if any change fails and return an updated proposal when the account has changed.

Instructions

Applies a proposal from propose_changes to the account. Only call this after the user has explicitly approved that proposal. All or nothing: every change is checked with Google first, and if one still fails the ones before it are rolled back. Each change is logged and, unless its summary says otherwise, can be reversed with undo_changes. If the account changed since the proposal, nothing is applied and the result (status "needs approval") is a new proposal with the updated summary: show it to the user and apply it only after they approve. When one request took several proposals (e.g. add exact negatives, delete the broad ones they replace), show the summaries together and, once approved, pass them all in proposal_ids: one apply, all or nothing, counted as one approved change.

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": "apply_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
proposal_idNoThe proposal_id a propose tool returned
proposal_idsNoInstead of proposal_id: several proposals for the same account that the user approved together, applied as one

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.35.0
    • addedInput schema / properties / proposal_ids
      Added value: +{
      +  "description": "Instead of proposal_id: several proposals for the same account that the user approved together, applied as one",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 50,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "proposal_id"
      -]
  2. Changed1 schema field changedv0.17.0
    • changedInput schema / properties / proposal_id / description
      Previous value: -"The id returned by propose_changes"New value: +"The proposal_id a propose tool returned"
  3. First observedv0.11.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare destructive, non-idempotent, open-world; the description goes well beyond them with atomicity semantics ('all or nothing', rollback of earlier changes), logging, per-change reversibility via undo_changes, and the stale-account behavior producing a status 'needs approval' proposal. That stale-state branch is exactly the kind of non-obvious behavior annotations cannot convey.

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 action and precondition, then layers rollback, reversibility, conflict handling, and the multi-proposal case. Dense and mostly economical, though the final sentence is long and could be split for readability.

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 destructive mutation with no output schema, the description covers approval precondition, atomicity, rollback, reversibility, logging, and the 'needs approval' return status. An agent has everything needed to call it correctly and interpret the outcome.

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 adds real meaning: proposal_ids is for several proposals the user approved together for the same account, applied as one atomic, single-counted change. It does not spell out that one of the two parameters must be supplied despite both being optional, which is the remaining gap.

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?

Opening sentence names a specific verb (applies) and resource (a proposal from propose_changes) and ties it to the account. It is immediately distinguishable from the propose_* siblings, which create proposals, and from undo_changes, which reverses them.

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 an explicit precondition ('Only call this after the user has explicitly approved that proposal'), names the reversal alternative (undo_changes), and prescribes the multi-proposal workflow: show summaries together, then pass them all in proposal_ids. When-not guidance is implicit in the approval precondition but concrete enough to act on.

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