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

Annotations already carry readOnly=false and destructive=false, but the description goes well beyond them by clarifying that this operation creates a draft, never publishes, leaves creatives in pending_approval, and enforces ceilings/linkedin_ads flag server-side. It also flags the currency-format difference for dailyBudgetUsd. No annotation contradiction exists.

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?

The description is a single dense paragraph with no filler: every sentence covers a distinct fact — purpose, publication status, approval step, currency shape, server enforcement. It front-loads the key draft/non-publishing distinction before details.

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 an 8-parameter mutation with no output schema, the description covers core side effects, the approval route, and an important parameter caveat. Its only notable gap is that it does not describe the return payload (e.g., the generated campaign/creative IDs), which an agent would need to chain the approval step without additional lookups.

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?

Schema coverage is 88%, so most parameter meanings are already documented. The description adds meaningful nuance by explaining that dailyBudgetUsd is a plain USD number while the stored campaign uses money objects, and by indicating how campaignId/icpId feed the derivation. That extra semantic value justifies a score above the high-coverage baseline.

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 opens with a specific action and resource: 'AI-generate a DRAFT ad campaign with creatives.' It also scopes the source (CampaignStack campaign and/or ICP) and clearly distinguishes the result from a live campaign by stating 'NOTHING is published to LinkedIn' and requiring campaignstack_approve_ad_creative before going live.

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?

It communicates the workflow context: generated creatives enter pending_approval and must be approved before going live, and server-side constraints apply. It does not, however, name a direct alternative such as campaignstack_create_ad_campaign for immediate publishing, so the when-not-to-use guidance is implied rather than explicit.

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