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

Annotations already declare non-readOnly, destructive, idempotent and open-world, and the description adds meaningful context on top: exactly which mutation is refused (REMOVED), what pausing does to serving, and that the result is a resource name plus confirmation. The 'never deletes' framing usefully softens the destructiveHint=true annotation by explaining the change is reversible; this is complementary, not contradictory. Permissions/auth requirements are not mentioned.

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 the one-line purpose, then refusals, then an Args block — efficient and scannable. The Returns block is mostly redundant since an output schema exists, which is the only place words are spent without adding value.

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?

A destructive write tool with four undocumented params and no schema descriptions is well covered: parameters, allowed values, what is refused, and the response shape are all addressed. Error behavior beyond the REMOVED case and auth/permission prerequisites are the remaining gaps.

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% (bare titles only) yet the description supplies meaning for all four parameters, including the practical detail that customer_id is numbers only with no hyphens and that status accepts only ENABLED or PAUSED. This fully compensates for the missing schema descriptions.

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 pair and resource ('Pauses or enables an ad') and the status semantics that follow make the operation unambiguous. Among the many set_*/update_* siblings, this is the only one scoped to an individual ad's status, so an agent can route to it without opening the 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?

Gives concrete guidance on what each status value does ('PAUSED stops the ad serving and ENABLED switches it back on') and a clear exclusion ('status REMOVED is refused'). It does not name the sibling tools (e.g. set_campaign_status, set_ad_group_asset_status) whose scopes differ, but the ad-level scope is implicit in the args.

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