Skip to main content
Glama

Change a Microsoft Advertising bid adjustment

msads_set_bid_adjustment
DestructiveIdempotent

Set a campaign's bid adjustment, in percent (20 = bid 20% more, -20 = 20% less, 0 = none), for a device, a location or a day/time slot. For devices this creates the adjustment if there is none. For a location or a day/time slot only an EXISTING one can be changed (see msads_get_targeting): adding one would also change where or when ads show, which this tool does not do. An adjustment above +100, or -100 on a device (which stops ads on it), needs allowLargeChange. Returns the previous adjustment so it can be restored. Use dryRun first when unsure.

Input Schema

NameRequiredDescriptionDefault
dayNoFor DayTime: the day.
dryRunNoPreview only. Microsoft has no validate-only mode, so Caybl reads the current value and shows exactly what would change (before and after) without sending anything. Free, and cannot affect spend.
toHourNoFor DayTime: end hour, 1-24.
fromHourNoFor DayTime: start hour, 0-23.
accountIdNoMicrosoft Advertising account id or account number (e.g. 'F123ABCD'), as listed by msads_list_accounts. Only needed when the sign-in can reach more than one account.
criterionYesWhat the adjustment applies to.
campaignIdYesCampaign id, from msads_get_campaigns.
deviceNameNoFor Device: Computers, Smartphones or Tablets.
locationIdNoFor Location: the Microsoft location id (shown by msads_get_targeting).
allowLargeChangeNoA change that more than doubles the current value is refused unless this is true. Set it only when the increase is deliberate and the user has confirmed it.
adjustmentPercentYesPercent change to bids: 20 = +20%, -20 = -20%, 0 = none.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already flag destructive/openWorld/idempotent, and the description adds real context beyond them: create-vs-update asymmetry per criterion, the +100/-100 thresholds, the stop-ads consequence of -100 on a device, and that the previous value is returned for restoration.

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?

Front-loads the core action and units, then layers the criterion-specific constraints in decreasing priority order. No sentence is redundant; the dryRun advisory closes the note usefully.

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 an 11-parameter mutation tool with no output schema, the description covers units, mode-dependent requirements, safety thresholds, response value, and preview advice — everything needed to call it safely.

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 baseline is 3, but the description adds percent semantics (20 = +20%, -20 = -20%, 0 = none) and criterion-conditional requirements that clarify which of the 11 parameters matter in each mode.

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?

States a specific verb and resource (set a campaign's bid adjustment) with the unit and the three criterion types it applies to. An agent can distinguish it from msads_set_keyword_bid or set_campaign_targeting without opening the schema.

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?

Explicitly scopes behavior: devices can be created, location/day-time must already exist (pointing at msads_get_targeting), and adding those would change delivery which this tool does not do. It also advises dryRun when unsure and allowLargeChange only for confirmed deliberate large increases.

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.

Resources