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

Adds substantial context beyond the annotations: the ad group is always created PAUSED, and an identical repeat call will not create a duplicate (idempotency). Neither fact is expressible via readOnlyHint/destructiveHint/openWorldHint, so this is genuine disclosure an agent needs to reason about side effects and retries.

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?

Front-loaded with verb, resource, and the PAUSED caveat, then organized by labelled blocks (context_hints, Gebote, workspace). Dense but every sentence carries operational information; the only minor cost is that the parameter notes run together without visual separation from the core action statement.

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?

An output schema exists, so return values need not be explained. For a 6-parameter creation tool with zero schema documentation, the description covers the non-obvious parameters, the bidding modes, currency conventions, the optional workspace slug, and idempotency — enough for an agent to call it correctly on the first try.

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 description coverage is 0%, so the description must carry the load — and it does for the ambiguous parameters: context_hints is explained as the main lever with a concrete example, and max_bid is spelled out per campaign type in account currency (CPM/1000 for impressions). Gaps remain: name, campaign_id, and description are not described at all, though the first two are self-evident required fields.

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 ("Anzeigengruppe in einer OpenAI-Ads-Kampagne anlegen") and immediately pins the scope to OpenAI Ads, which separates it from the many other ad-group creation tools in the sibling list (ads_create_ad_group, meta_create_adset). It also front-loads a key behavioral fact — the group is always created PAUSED — so the agent knows the resulting state before calling.

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?

Gives clear operational context: bidding only applies to clicks/conversions campaigns with a daily budget, and omitting max_bid triggers automated bidding. However, it never explicitly says the campaign must already exist or routes the agent to a sibling (e.g., create the campaign first, or use openai_ads_list_ad_groups to check for duplicates) — despite guaranteeing idempotency, mention of the natural prerequisite/alternative would push this to a 5.

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