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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful scope ('in this account's Metadata library'), implying the ad must already exist in the account, but says nothing about behavior when a link cannot be resolved, whether partial results are returned, or the cost of scanning pages — gaps the annotations don't fill.

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 sentence, front-loaded with the concrete input formats and ended with the reason to call it. No redundant restatement of the title and no filler.

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?

There is no output schema, so the description should describe the return: does it return ad records keyed by the requested link, what an unresolved link looks like, and whether unmatched entries are reported? The phrase 'to the ads in this account's Metadata library' hints at the result but leaves the resolution semantics and failure mode undefined.

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 all three parameters (links, max_pages, campaign_ids) are already documented, including the default of 20 pages and the 20-link cap. The description's URL format parenthetical duplicates the schema rather than extending it; it adds nothing about campaign_ids scoping or scan cost. Baseline 3 is appropriate.

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 (map/resolve), the exact input forms accepted (linkedin.com/ad-library/detail/<id>, sponsoredCreative URNs, bare creative ids), and the target resource (ads in this account's Metadata library). That input signature clearly separates it from siblings such as search_library_creatives_by_name or fetch_creative_details, so an agent can pick it without opening the 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?

The closing clause gives a concrete use case: resolving when the user supplies a LinkedIn link so the ad can be REUSED in a new campaign rather than rebuilt. It does not name an alternative path (e.g. name-based search) or state a when-not-to-use condition, so it stops short of full routing guidance.

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