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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description's added value is real: it discloses newest-first ordering, a 12-item page size, the nextOffset cursor, and an ad_status=unavailable fallback for ads no longer in the library. It omits permission/auth requirements and the offset ceiling, keeping it just short of a 5.

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 short sentences, each carrying distinct information (scope, filtering, item shape, pagination) with the most decision-relevant facts first. No filler or restatement of the tool name.

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 does the work of describing return values: item contents (saved note plus ad summary) and the unavailable-ad edge case. It leaves small gaps around the offset bound and whether the collections list is itself paginated, but an agent has enough to call and iterate correctly.

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%, so the description must compensate, and it largely does: collectionId is explained as restricting to one *owned* collection (a meaningful constraint the UUID schema does not convey), and offset is covered indirectly through '12 per page' and 'Follow nextOffset'. The 10000 offset maximum and whether collections themselves are truncated remain unstated.

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 ('List the caller's own saved ads') plus scope, ordering, and page size in a single front-loaded sentence. The word 'saved' plus 'caller's own' inherently separates it from search_ads and save_ad among the siblings.

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 explains what collectionId does ('limits the page to one owned collection'), which implies when to use it, but never names an alternative such as search_ads for broader library browsing or states when not to use this tool. Usage is inferable rather than explicit.

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