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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the safety profile is covered. The description still adds real value on behavior: no automatic publishing results from the call, and it names the manual submission path that must follow. It does not discuss permissions or what existing published items do after the switch, so it sits at solid-but-not-complete.

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-loads the mode change and its consequence, then the usage, then the alternative, then the return shape and parameter sourcing. Dense and information-rich, though the inline return-shape and the parenthetical error path make the final sentences harder to scan than necessary.

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 two-parameter mutation with no output schema, the description covers what is returned ({integrationId, action, status, kind, editUrl, message}), the error path for project_id, and the follow-up submission tools. Nothing an agent needs to invoke it correctly 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?

Schema coverage is only 50% (project_id has no description), and the description compensates fully: ad_id comes from list_ads, project_id is OPTIONAL, inferred for single-project customers, otherwise project_id_required is returned and list_projects should be called. That is exactly the error-path detail the schema omits.

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 ('Switch an ad to MANUAL product mode') and immediately defines the operational meaning: nothing is published automatically, items reach the channel only via submit_ad_items / submit_all_ad_items. That distinguishes it cleanly from set_ad_auto_mode and from the submit siblings 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?

Gives two concrete use cases ('test before activating', 'stop automatic publishing'), states what the tool does NOT do ('sends nothing to the channel'), and names the alternative for a related goal ('to stop all syncing use pause_ad'). This is explicit when-to-use plus routing to a sibling.

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