New ads since a time

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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds genuinely non-obvious behavior: promoted old ads are excluded by date, `more` signals that the page limit was hit, and nothing is stored or pushed (stateless cursor polling). The only gap is how far back the cursor can reach or what happens if `since` is stale.

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 what the tool returns and then the polling contract. Nothing is redundant against the schema despite the tool having 17 parameters.

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 usefully surfaces return-side signals (`latest`, `more`) and the exclusion of promoted ads. It leaves a few operational questions open for a 17-param, nested-object tool, such as cursor expiry, but it is adequate for correct invocation.

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 100%, so the schema already documents all 17 parameters, including the `since`/`hours` relationship and the `latest` convention. The description reinforces the `since`-from-previous-`latest` loop but adds no format or validation detail beyond the schema, so the 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?

The description names a specific verb and resource ('Ads published after a moment, newest first') and states the tool's distinctive behavior as a polling cursor over a saved search. It distinguishes itself from a one-shot search by describing repetition-free polling, though it never names its nearest sibling (dv_search or dv_watch) explicitly.

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?

It gives a concrete operating loop: call it, remember `latest`, pass it as `since` next time, and let a caller or scheduler decide when to poll. That is clear when-to-use guidance, but there is no explicit when-not-to-use or routing statement against dv_search/dv_watch.

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