promote_campaign_draft

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

The description adds substantial behavioral context beyond the sparse annotations: promotion is asynchronous and returns immediately without waiting, it overwrites live campaign behavior, and it documents the full status progression PROPOSED -> PROMOTING -> PROMOTED (or PROMOTE_FAILED). It also discloses the two-phase preview/commit safety mechanism. This is consistent with annotations (readOnlyHint=false, destructiveHint=false); no contradiction.

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

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

Four dense sentences with the critical live-traffic warning front-loaded in the first sentence. Each subsequent sentence earns its place: the two-phase call in sentence two, asynchronous behavior in sentence three, and verification steps in sentence four. There is zero filler.

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

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

For a moderately complex tool (async execution, two-phase confirmation, state transitions), everything an agent needs is present: what happens, what gets overwritten, how to preview safely, how to confirm, and where to verify the outcome with exact status transitions. Since an output schema exists, not documenting return values is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage the description carries the full burden, and it delivers the key semantic for confirm_token: absent means preview, present means execute — meaningfully expanding the schema's bare 'default: ""'. draft_resource_name's role is inferable from the overall description context, but customer_id is never mentioned and is only interpretable by convention shared across sibling tools.

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

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

The description states a specific verb and resource: 'Promote a campaign draft's edits back into the live base campaign.' It also differentiates this from its draft-workflow siblings by explicitly flagging it as the one action in that workflow that touches live traffic, so an agent can distinguish it from create_campaign_draft, list_campaign_drafts, and remove_campaign_draft.

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

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

The description gives explicit call-sequence guidance: call without confirm_token to preview (showing which campaign it would overwrite), then call again with the token to execute. It also directs the agent to list_campaign_drafts afterward to observe the outcome. However, it never explicitly names alternative tools or states when not to use this one — the exclusion of siblings is implicit ('the one action in the draft workflow that touches live traffic').

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