Skip to main content
Glama

Change history

change_history
Read-only

Retrieve a Google Ads account's proposal history to see applied, failed, and undone changes, plus when measurable results become ready.

Instructions

Every proposal made through Camberstack, with what was applied, what failed, and what was undone. Applied Google Ads changes that can be measured carry change_results: ready, or the date their results start.

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": "change_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost proposals to return, newest first
customer_idNoGoogle Ads customer ID, with or without dashes (from list_accounts)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds real value by enumerating the proposal states captured (applied, failed, undone) and explaining the change_results field's ready/date semantics. It omits ordering, pagination behavior beyond the limit default, and whether results span all accounts when customer_id is omitted — notable for a history tool.

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?

Two sentences with no filler, and the core scope statement comes first. The second sentence is slightly awkward in construction ('carry change_results: ready, or the date their results start') and about a response field rather than tool selection, but it is not wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must carry the return-value burden; it partially does by describing proposal statuses and the change_results field. For a read-only history tool with a customer_id filter, it should also state whether results are per-customer or global and how the list is ordered/paginated, which it leaves implicit.

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 description coverage is 100%, with both limit ('Most proposals to return, newest first') and customer_id documented inline, so the baseline is 3. The description adds nothing about either parameter and does not answer the scoping question of whether omitting customer_id aggregates proposals across all accounts.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and scope: 'Every proposal made through Camberstack, with what was applied, what failed, and what was undone,' which tells an agent exactly what dataset is returned. It lacks an explicit verb ('list'/'retrieve') and does not distinguish itself from siblings such as change_results or propose_changes, though the 'every proposal' framing implicitly separates it from outcome-specific tools.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no alternative named, and no prerequisites stated. An agent cannot tell from the description whether to reach for this versus change_results, apply_changes, or discard_proposal when investigating a proposal's fate; only the purpose text implies audit-style retrieval.

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