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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the bar is lower, but the description still adds genuinely useful behavior: the ad is created PAUSED (a critical fact for a live-write tool) and 'WRITES live' restates the mutation surface. It does not cover permissions/scopes, whether the creative is auto-published, or error behavior, keeping it short of a 5.

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 short clauses, all front-loaded: what it does, its resulting state, its input modes, and its write semantics. No filler, and no sentence could be removed without losing a decision-relevant fact.

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 11-param, no-output-schema mutation tool, the description covers the essentials an agent needs to act: target entity, creative sourcing options, and the PAUSED default. What remains unstated is the return value (presumably an ad id) and the conditional parameter requirements for the ad-copy path, which is the main risk of a malformed call.

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 only 27% schema description coverage across 11 parameters, the description carries weight, and it does clarify the ambiguous creative_id vs image_hash vs copy-fields choice. However, it is silent on the conditional dependencies among the remaining params (page_id, website_url, headline, primary_text, cta are all unnecessary for the creative_id path but likely required for the copy path), and meta_account_id is unexplained, leaving a substantial gap.

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?

States a specific verb and resource with explicit scoping: a NEW ad with creative into an EXISTING ad set. The caps on NEW/EXISTING/Pausal preempt the most common confusion (creating ads vs. ad sets, or duplicating creatives), so an agent can separate this from list_ads, get_creative_library, or bulk_create_campaigns without opening a schema.

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 clearly frames the three mutually exclusive ways to supply creative content (existing creative_id, library image_hash, or inline ad copy), which is the real decision point when calling this tool. It implies contrast with a bulk path ('this is where saved library creatives CAN be used', 'unlike bulk-create' in the schema) but never names a sibling tool or states when NOT to use this one.

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