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

Annotations already declare a read-only, idempotent, non-destructive, closed-world lookup, so the safety profile is covered. The description adds real value beyond that: the meaning of the lift value, the verdict vocabulary, and the 'final=false' still-measuring state that settles on finalOn. However it never says what a result record contains or how paging interacts with the free-tier limit.

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 first clause is well front-loaded with the dataset scope, and the lift formula is defensible detail given there is no output schema. But the body degenerates into one long run-on that interleaves metric math, verdict tokens, a flag, a country list, and an account limitation with no separating structure, making it harder to scan than it needs to be.

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 nine-parameter filtered search with zero schema description coverage and no output schema, the description omits any explanation of the filters, which is the largest gap an agent faces when constructing a call. It does cover the result metric and the free-tier truncation, but a caller still cannot confidently choose values for sort, effect, period, or kind from this text.

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% across nine parameters, so the description must compensate and largely does not. The enumerated country list does add meaning beyond the two-letter regex for `country`, but `q`, `kind`, `sort`, `page`, `chart`, `effect`, `period`, and `genreId` are entirely unexplained — notably `sort` values like 'visual' and 'impact' and what `effect=measured` versus `lift` mean.

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 identifies the resource precisely ('icon and screenshot redesigns of top-chart apps' and their post-change rank movement), but never states the operation — there is no verb like 'search', 'list', or 'return matching changes'. An agent can infer it is a lookup over a creative-change dataset, but cannot tell from the text alone how it differs from siblings such as get_app_creative_history or trending_apps.

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 when-to-use guidance and no named alternative. The only contextual note is an access constraint ('Free accounts see the first few results'), which tells the agent about truncation but not when this tool is the right choice over the sibling creative/history tools.

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