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

Annotations already declare the tool is not read-only and is idempotent; the description adds that synchronization restarts, that ads have no order sync, and the exact response shape. This goes beyond annotations, though it could say more about side effects; there is no contradiction.

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?

The description is dense but every sentence adds value: action, scope and exclusions, return payload, and parameter sourcing. The phrase 'Ads are ads-based channels' is slightly tautological, but overall the structure is efficient and front-loaded.

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?

With no output schema, the description includes the return payload. With a sparse schema, it covers both parameters and even handles the project_id edge case. With sibling tools like resume_marketplace and resume_feed, it clarifies the ads-specific context, making selection and invocation unambiguous.

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%, so the description must compensate. It explains that ad_id comes from list_ads and clarifies project_id's optionality with the single-project inference rule and the project_id_required case referring to list_projects. Both parameters are meaningfully documented.

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?

Opens with a specific action and resource ('Resume a paused ad') and immediately distinguishes ads from marketplaces by defining what an ad is and what it does not do ('no order sync'). This makes it easy to tell resume_ad apart from sibling tools like resume_marketplace and pause_ad.

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?

States the condition for use (ad is paused, synchronization should restart) and explicitly narrows applicability to ads-based channels, not marketplaces. It also gives concrete routing guidance for the optional project_id: inferred for a single-project customer, otherwise call list_projects.

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