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

Annotations already establish non-read-only, non-idempotent, non-destructive behavior. The description adds critical context beyond them: it spends credits, renders each ad, requires human confirmation, creates only draft campaigns, and is asynchronous via get_ad_campaign polling.

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?

Four compact sentences, front-loaded with the action and cost warning. Every sentence contributes useful information with no boilerplate.

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 complex credit-spending rendering workflow, the description covers input origin, outputs, cost, human-in-the-loop confirmation, non-publication, and the required polling follow-up. An output schema exists, so return-value details need not be repeated.

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?

There is only one parameter, and schema description coverage is 100%; the schema already explains plan as the object from plan_ads, as-is or edited. The tool description references the plan but adds no meaningful format, validation, or editing semantics beyond the schema, so baseline 3 applies.

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 action (make ads) and concrete outputs: a draft campaign per platform and Siren-rendered ads. It also distinguishes this from publishing with 'Nothing reaches the platform yet' and points to plan_ads/get_ad_campaign context, so siblings are clearly separable.

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 clear operational context: use the plan from plan_ads, poll get_ad_campaign afterward, and tell the human first because credits are spent. It implies it is not the go-live/send tool, but it does not explicitly name alternatives such as send_ads_to_platform or go_live_ad_campaign.

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