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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds what that means in practice — resuming restarts automatic publication to the live channel — and requires user confirmation. It also spells out the return payload ({integrationId, action, status, kind}), which no output schema provides.

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 core action and effect, then behaviors, return shape, and parameter rules in a sensible order. There is mild redundancy between 'synchronization to the channel starts again' and 'when the user wants a paused ad to sync again', but nothing is padding.

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?

Complete for a mutation tool with no output schema: the side effect, the confirmation requirement, the parameter sourcing, the fallback path, and the response shape are all present. An agent has everything needed to call it correctly and safely.

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%, so the description must carry both parameters, and it does: ad_id is sourced from list_ads, and project_id is optional with a clear decision rule (inferred for single-project customers, otherwise project_id_required and call list_projects). No ambiguity is left for a 2-parameter tool.

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 ('Resume a paused ad') and immediately defines the effect ('synchronization to the channel starts again'). It also defines what an ad is versus a marketplace, which lets an agent separate this from the many marketplace/feed siblings without opening a 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 an explicit when-to-use condition ('when the user wants a paused ad to sync again') plus a prerequisite workflow ('Confirm with the user before resuming') and the project_id escalation path to list_projects. It never names the counterpart sibling (resume_marketplace) directly, relying on the ads-vs-marketplaces definition instead.

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