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

Annotations already declare destructiveHint=true, idempotentHint=false, openWorldHint=true and non-read-only, so the safety profile is covered. The description adds context beyond that: the ad group is created paused with no spend, no approval flow is triggered, budget fields only apply to campaigns without a budget, and conversion objectives require pixel_id plus an event. It stops short of saying what is returned or what permissions/account scopes are needed.

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 purpose is front-loaded, but the remainder is a single run-on paragraph mixing Meta, Google and Microsoft specifics with no separation, making it hard to scan for the platform in use. The length is defensible for 24 params, but the lack of structure wastes reader effort.

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 24-field, nested-object mutation with no output schema, the description covers the important semantics: defaults, budget constraints, conversion requirements and placement fallbacks. Gaps remain around the returned identifier and whether the parent campaign must be in a particular status, but nothing critical to a correct call 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?

With 24 parameters at 42% schema coverage, the description carries the burden and largely does: it explains cross-field constraints (budget_minor/lifetime_budget_minor only for unbudgeted campaigns, lifetime requires end_time, custom_event_type must match the custom conversion, advantage_audience must be set explicitly, age range 13–65) and the source tools for countries/regions/cities/interests. Several parameters, notably page_id, languages and the placement sub-fields, are only covered by schema text.

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 opening clause states a specific verb and resource ('Create a paused ad group in a campaign') and immediately discloses the default state, which distinguishes it from create_campaign and create_ad. It never names those siblings explicitly, so differentiation is inferred from the resource noun rather than stated.

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?

'no spend, no approval needed; enabling is a status proposal' gives useful context that this tool is safe to call without the propose_change/approve_change flow, which is real guidance. However, it never states prerequisites (existing campaign, matching campaign type) or when to choose this over create_ad or a platform-specific change tool; usage is implied rather than stated.

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