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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description's one contribution beyond that is the "newest first" sort order, which is genuinely useful and not in the annotations. It says nothing about pagination, default page size, or what an empty account returns.

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?

One clause, front-loaded, zero filler. It is terse to the point of being a fragment, but nothing is redundant and no sentence fails to earn its place.

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 simple list tool with a full read-only annotation set and no output schema, the description gives just enough to know the ordering of results. It is incomplete on paging behavior and the default `limit`, which matter for actually invoking it well.

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 67%: `before` and `api_key` are documented in the schema, but `limit` (1-100) has no description anywhere, so its default is unknown. The description adds no parameter meaning at all, leaving the most likely knob for controlling response size unexplained.

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?

"The account's ads, newest first" names the resource and its ordering, but supplies no verb and never says it is a listing/retrieval operation. It is distinguishable from get_ad only by inference from the ordering claim, not by any explicit contrast.

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?

There is no guidance on when to call this versus get_ad, list_ad_formats, or the pause/archive/resume tools. The agent must infer from the name alone that this returns a collection rather than a single ad.

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