Skip to main content
Glama

ADS Beast

prepare_campaign_bid_strategy_change

Prepare a new bid strategy for one campaign, with its target cost per conversion or target ROAS. target_cpa is in whole units of the account currency; the preview shows the figure the platform receives. Changes nothing: stores a preview_id (15 min, single use) to show, then execute_prepared_change.

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": {
      "campaign_id": "<campaign_id>",
      "bid_strategy": "<bid_strategy>",
      "reason": "<reason>"
    },
    "name": "prepare_campaign_bid_strategy_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhy, with numbers (shown to the approver).
target_cpaNoTarget cost per conversion in the ad account's currency, whole units. For target_cpa only.
campaign_idYesADS Beast id from list_campaigns, not the platform's.
target_roasNoTarget ROAS as a ratio, for example 4.0 for 400%. For target_roas only.
bid_strategyYesThe bid strategy to switch to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false/destructiveHint=false/openWorldHint=true, which alone would not tell an agent that the campaign is untouched. The description adds that this is a pure preview with a 15-minute, single-use preview_id and that the preview reports the figure the platform actually receives. It stops short of covering approval flow, preview contents, or what happens if a preview expires or is superseded.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no filler: purpose and scope first, unit semantics second, the non-mutating/preview contract and next step last. Every clause carries operative information for calling the tool.

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?

With five parameters, one enum, no nested objects and no output schema, the definition covers what an agent needs: what it targets, what units to pass, that nothing is mutated, that a preview_id is returned with a 15-minute single-use lifetime, and which tool finishes the job. Only minor items (preview refresh/expiry recovery, approval implications) are absent.

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; the description still earns credit by tying target_cpa to 'whole units of the account currency' and adding the round-trip detail that the preview displays the value as the platform receives it. The conditional pairing of target_cpa vs target_roas is largely duplicated from the schema, which keeps this short of a 5.

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?

Names a specific verb and resource ('Prepare a new bid strategy for one campaign') and scopes it with the exact inputs it accepts (target CPA or tROAS). It is immediately distinguishable from sibling prepare_* tools (budget, pause, enable) and from the terminal execute_prepared_change step.

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

Usage Guidelines4/5

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

Explicitly establishes the two-step workflow: this tool 'Changes nothing' and instead stores a preview_id, and the follow-up action is named (execute_prepared_change). It does not state when an agent should prefer campaign_strategy_expert_review or generate a strategy first, so the alternative-selection guidance is present but not exhaustive.

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.