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

With zero annotations, the description carries full responsibility for behavioral disclosure. It reveals the campaign is always created PAUSED, that a Merchant Center link is required (with a clean error if absent), that merchant_id auto-resolves when exactly one link exists, that dry_run validates without creating, and that campaign_priority only arbitrates within the account's own standard Shopping campaigns. It even notes that language targeting does not exist for Shopping. This is comprehensive behavioral transparency.

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 long but every sentence earns its place. It front-loads the core creation scope, then flows naturally into prerequisites, dry_run workflow, bidding nuances, and sibling alternatives. The information is dense but structured logically, making it easy for an agent to parse and act on.

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 complex tool with five parameters, nested objects, no output schema, and no annotations, this description covers essential context: the atomic one-shot nature, the always-paused behavior, the Merchant Center prerequisite, the dry_run flow, bidding strategy constraints, feed label handling, and explicit sibling comparisons. Nothing an agent needs to call it correctly is missing.

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?

The description adds crucial meaning beyond the schema: ad_account_id must be a bare 10-digit ID, daily_budget is in plain currency not micros, bidding_strategy 'auto' means Maximize Clicks while 'manual_cpc' requires cpc_bidcher, feed_label must match exactly and is case-sensitive, and campaign_priority's interactions with PMax are explained. With schema coverage at only 20%, this compensating detail is vital for correct invocation.

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 verb and resource: 'Create a complete standard Google Shopping campaign in ONE atomic request.' It then enumerates the exact components (budget, campaign, ad group, product ad, listing group), and distinguishes itself from PMax and Meta catalog siblings by naming them explicitly. This is a model of purpose clarity.

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 when-to-use and when-not-to-use guidance: it instructs to dry_run first DB, says to use adsap_google_create_pmax_campaign for PMax and adsap_create_campaign for Meta catalog ads, and explains the trade-offs between bidding strategies (manual_cpc as the reason to prefer Shopping over PMax). This is far beyond minimum viability.

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