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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write. The description adds meaningful behavior beyond them: the entity is created PAUSED by default and confirm gates a dry-run preview. It omits auth/permission requirements, but the added context is substantive.

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?

A single dense, front-loaded sentence that packs the operation, default state, and both key parameter meanings with no filler. Efficient, though it reads as a run-on string of facts.

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 described, and annotations cover the safety profile. The description supplies the key behavioral facts (paused default, preview mode) and the trickiest param semantics, leaving only minor gaps for a straightforward create operation.

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% across 7 parameters, so the description must compensate. It explains cpc_bid, language (with examples and the Microsoft requirement), and confirm, but leaves account_id, campaign_id, customer_id, and name undefined. Partial compensation only.

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 ('Creates an ad group in a campaign') and scopes it to the Microsoft platform via the name and language example. It does not explicitly distinguish itself from generic siblings like create_ad_group, but the platform context is clear.

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 confirm=false/confirm=true hint effectively describes a preview-vs-apply usage mode, which is genuine guidance. However, it never states when to choose this tool over siblings like create_ad_group or create_microsoft_campaign; usage is implied rather than spelled out.

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