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

With no annotations provided, the description does disclose two real traits: it is read-only and it is paginated, plus the polling advice. It omits ordering/recency of events, retention window, and permission requirements — meaningful gaps for a feed tool where an agent must decide whether to poll repeatedly.

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?

Three short, front-loaded sentences with zero filler: what it returns, how to consume it, and its safety profile. Nothing could be cut without losing information.

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?

No output schema and no annotations, so the description is the only source of behavioral detail — and it never describes event shape or ordering, which matters for a paged feed. Adequate to select the tool, thin for invoking it well over multiple pages.

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 coverage is 75%, so the schema already documents id, limit, and offset. The description's category list merely echoes the enum values already present in the schema rather than explaining their semantics (e.g., what 'system' vs 'billing' events contain), so it adds little beyond structured data.

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+resource ('Paged activity events of a campaign') and enumerates the event categories, which goes beyond restating the name. It doesn't name a sibling to disambiguate against similarly-scoped tools like get_campaign_pulse or get_campaign_monitor, so it falls short of a 5.

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?

'Poll it instead of a live stream' gives an implied usage pattern (repeat calls rather than subscribing), which is genuine guidance. But it offers no when-to-use/when-not against the many campaign-reading and activity-feed siblings, and no exclusions.

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