Get In-App Campaign Stats

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), so the description clears the lower bar easily and then adds substantial behavior: rates are fractions 0–1 and null when there is no denominator, totals span the campaign's whole life, and figures are recounted periodically so fresh campaigns can legitimately read 0. This is exactly the kind of non-obvious behavior an agent needs to avoid misreporting zeros.

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 the purpose and metric list, followed by two compact sentences on rate format and staleness. Every sentence earns its place, though 'every 15 minutes for email' is a slightly off-channel detail inside an in-app tool and momentarily muddies the channel framing.

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 must convey the return surface, and it does by naming all five metric families plus the rate encoding and null semantics. It stops short of describing the response envelope or key names, but an agent has enough to call and interpret the result 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?

Only one parameter exists and its schema description coverage is 100% ('The in-app campaign id' with a UUID pattern), so the schema carries the semantics. The description adds the scoping notion of 'one in-app campaign' (single-campaign, not list), but nothing about id format or sourcing beyond that. 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?

The description opens with a specific verb and resource ('Get how one in-app campaign performed') and enumerates the exact metrics returned: impressions, clicks, dismissals, expirations and devices reached. It distinguishes itself from delivery-oriented siblings by noting 'Nothing is sent on this channel, so there are no delivery or failure counts.' It does not explicitly contrast with get-in-app-campaign (config) or the email/push/sms stats siblings, so it falls short of full sibling differentiation.

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?

There is real usage guidance, but it is about interpreting results rather than choosing the tool: 'check again later rather than reporting that nothing was delivered' for recently sent campaigns. Nothing states when to prefer this over get-in-app-campaign or the other channel stats tools; the channel distinction is implied by the name only.

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