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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: an Ad never observed returns not_found, and continuation is via next_cursor. It does not state what happens with an invalid library value or whether limit affects the response shape, but for a read-only lookup the added context is reasonable.

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 use case and exclusions, and the whole definition is a few short lines with no filler; 'Price: Free' is legitimate cost metadata for an agent. The fragment 'library plus the id search_ads or get_tracker_ads returned.' is grammatically clipped and slightly harder to parse than surrounding sentences.

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?

An output schema exists, so return-value detail is unnecessary, and the description covers the two things an agent actually needs to handle: not_found for never-observed ads and next_cursor pagination. It stops short of describing the limit parameter's default or effect, which is the one loose end for a 4-parameter lookup tool.

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 25% – only 'id' is documented, and the schema merely says 'The Ad's library id.' The description compensates by explaining that library and id come from search_ads or get_tracker_ads, and that next_cursor drives paging, which is real value. However, 'limit' (1-100) and the meta/tiktok library semantics are left entirely to the schema, so the low-coverage gap is only partly closed.

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 ('one stored Ad's history') and enumerates exactly what the history contains: running state, placements, countries, disclosed spend and reach. It also explicitly negates the two nearest siblings (get_ad for details, get_tracker_ads for an advertiser's ads), so an agent can disambiguate 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?

Opens with an explicit 'Use when' condition and pairs it with two named 'Not for' exclusions routing to get_ad and get_tracker_ads. It further states the prerequisite path for the required arguments ('library plus the id search_ads or get_tracker_ads returned'), which tells the agent how to obtain valid inputs.

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