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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true. Beyond those, the description adds two real behavioral facts an agent cannot get elsewhere: the UNDER_REVIEW preclusion on pausing, and the preview mode via confirm=false. It stops short of describing permissions or reversibility of ARCHIVED.

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?

Two short sentences, front-loaded with the operation and its value set, followed by the constraint and the preview switch. No padding or redundant restatement.

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 no explanation, and the destructive/preview semantics are covered. Remaining gaps are minor: no auth/permission prerequisites and no mention of what a status change does to an ad currently delivering.

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 4 parameters, so the description is the only source of parameter meaning. It documents intended_status (via the enum list) and confirm (preview semantics), but says nothing about account_id or creative_id. Partial compensation for a total schema gap.

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+resource ('changes a creative's (ad's) intended status') and enumerates the four valid target states, which is far more than a restatement of the name. It does not discriminate against the very similar siblings update_ad_status / update_microsoft_ad_status / update_tiktok_ad_status, so an agent must infer LinkedIn-scoping from the name alone.

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 = preview' clause effectively tells the agent how to dry-run before committing, which is useful guidance. However there is no explicit when-to-use or when-not-to-use statement relative to the other status-update tools in the sibling list.

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