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

With no annotations present, the description carries the burden well: it discloses an external provider call, a persisted write ('store them'), a per-campaign rate limit (once per minute), and that it consumes no credits. It omits what happens if the rate limit is hit and whether existing stored counters are overwritten.

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 sentences, front-loaded with the action, then the constraint, then the cost note. Nothing is wasted and every sentence contributes operational 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?

For a one-parameter tool with side effects and no annotations or output schema, the description covers source, persistence, throttling, and cost. The only real gap is the return shape (does it return the refreshed counters or just an acknowledgement), which no schema supplies either.

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 100% and the single `id` parameter is already documented as a campaign UUID from list_campaigns. The description adds only the notion that the counters apply 'per campaign', which is marginal beyond the schema — baseline 3 applies.

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 action and resource: pull sent/opened/clicked/replied/bounced counters from the sending provider and persist them. The 'refresh/store' framing implicitly separates it from read-only siblings like get_campaign_email_stats, but no sibling is named explicitly.

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?

'Max once per minute per campaign' implies the tool is for on-demand freshness rather than bulk reporting, but the description never says when to prefer this over get_campaign_email_stats or get_campaign_analytics, nor what happens on a too-frequent call.

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