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

Beyond the destructiveHint=true annotation, the description adds the highest-value operational facts: activation starts real ad delivery and therefore incurs cost, and archiving is irreversible and deliberately excluded. It also discloses the read-back verification behavior (status_before, status_after, verified), which tells the agent it can confirm the mutation took effect.

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?

Everything is front-loaded onto the action and the object types, with the safety and cost warnings following immediately. The prose is dense and every clause carries information, though the compressed telegraphic phrasing (bare 'object_type:' / 'status:' fragments) costs a little readability.

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 4-parameter mutation tool with an output schema, annotations, and destructive semantics, the description covers the safety profile, the cost consequence, the excluded operation, and the verification fields. The main residual gap is the meaning/format of object_id, which neither schema nor description explains.

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 coverage is 0% with no enums, so the description carries the full burden — and it delivers: it enumerates the legal values for object_type and status, and explains that workspace is a customer workspace slug that may be omitted when only one workspace exists. Only object_id is left undocumented, which keeps it below a perfect score.

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 description states a specific verb pair ('pausieren oder aktivieren' / pause or activate) plus the exact resources it applies to: campaign, ad group, or ad. It also names the target scope field explicitly ('object_type: campaign, ad_group oder ad'), so an agent can distinguish this status-toggle tool from create/update siblings such as openai_ads_update_campaign without opening any 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?

It gives clear when-to-use guidance (pause to stop delivery, activate to start it) and an explicit when-not carve-out: archiving is impossible here and must be done in the Ads Manager. It stops short of routing the agent to the sibling that handles other mutation types, but the boundary it does draw is precise and actionable.

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