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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) it discloses that the campaign is always created paused, that objective is immutable after creation, that exactly one of daily/lifetime budget is allowed with a EUR minimum of 15, that automatic bidding requires daily_budget, and that a repeated identical call is idempotent. These are exactly the behavioral facts an agent cannot infer from structured fields.

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?

Purpose and the critical 'always paused' fact are front-loaded, followed by workflow and then per-parameter constraints; every line carries actionable content. The telegraphic multi-clause style is dense but not padded, though it could be broken into clearer labeled segments.

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-parameter, open-world mutation tool this covers creation state, ordering, dependencies, budget rules, defaults, date semantics, and idempotency. An output schema exists, so return values need not be explained, and 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?

Schema description coverage is 0%, so the description carries the full burden and does so: objective values and immutability, budget mutual exclusivity and currency/minimum rules, location_ids sourcing, platform value list, date format/timezone/inclusivity, workspace semantics, and the conversions dependency. Only the trivial 'description' field is left undocumented.

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 ('Neue OpenAI-Ads-Kampagne ... anlegen') plus the platform scope (ads in ChatGPT) and the key invariant (always created PAUSED). It also implicitly distinguishes itself from openai_ads_create_ad_group and openai_ads_create_ad by placing itself first in the creation chain.

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 an explicit ordered workflow (campaign → create_ad_group → create_ad → set_status only after asking the customer) and names the prerequisite tools for dependent values (openai_ads_conversion_setup for conversion_event_setting_id, openai_ads_search_locations for location_ids). It even flags a dangerous default ('ohne Angabe: alle verfügbaren Länder — fast nie gewollt').

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