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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description instead adds interpretive behavior that annotations cannot: 'delivering' is true only for LinkedIn status RUNNABLE, 'unknown' bid strategy means a new unmapped LinkedIn value (read optimization_target instead), and amount is null under maximum_delivery. It also flags that targeting name resolution is best-effort with urn fallback. Much of the block is return-shape documentation that the existing output schema already carries, which keeps it below 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?

Front-loaded with purpose and organized into scannable bullet groups, which is good structure. But the bulk is an exhaustive field-by-field description of the response that largely duplicates the output schema, making the definition long for what is a three-parameter read. Several return-field sentences do not earn their place against an existing output schema.

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 read-only list tool with annotations and an output schema, an agent has nearly everything needed: hierarchy semantics, targeting AND/OR logic, bid-strategy caveats, and the include_targeting tradeoff. The missing piece is pagination/count behavior, which matters for a listing call but is the only substantive hole.

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 carries the full burden, and it explains two of three parameters well: include_targeting as a cost/benefit switch for name resolution, and workspace as an optional slug when only one workspace exists. The third parameter, count (default 50), is never mentioned and no pagination behavior is described — a meaningful gap for a list tool.

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 concrete verb and resource ('LinkedIn-Kampagnen des Ad-Accounts') and enumerates the content dimensions returned (settings, bid, delivery status, targeting). The parenthetical mapping to Google/Meta ad-group level is a genuinely useful disambiguation of hierarchy. It does not, however, name the nearest LinkedIn siblings (linkedin_list_campaign_groups, linkedin_campaign_performance), so routing among those is left to inference.

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?

Usage is implied rather than stated — the agent must infer that this is the enumeration tool versus the performance-reporting or campaign-group tools. The one real guideline is parameter-scoped: 'include_targeting: false spart die Namensauflösung, wenn nur Gebot/Status gebraucht wird.' No when-not-to-use or alternative-tool routing is provided.

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