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

Annotations only declare readOnly/openWorld, but the description adds meaningful interpretive behavior: delivered is device-confirmed, large sends are sampled (so counts can be approximate), campaigns (ngr_...) return whole-campaign plus per-platform and deduped figures, while single notifications only return per-version breakdowns. These are exactly the caveats an agent needs to report numbers honestly.

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 front-loaded sentence that opens with the core scope and then enumerates return contents. The telegraphic style ('devices tried, sent, failed...') is dense but every clause carries information; nothing is padded.

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 describe the returned data, and it does so thoroughly, including the campaign/deduped variants and the sampling caveat. The remaining gap is parameter-level detail (ID format, source), which is minor for a one-parameter read tool.

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 must compensate. It hints that the ID may be a campaign identifier prefixed 'ngr_...' and that behavior differs for such IDs, which is genuine added meaning, but it never states the ID format or where to obtain it, leaving the single parameter only partly documented.

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 names the resource (one notification) and enumerates the result categories (devices tried, sent, failed, delivered, clicked, per-version). That is specific enough to separate it from list_notifications (which enumerates) and preview_notification (which simulates a send), though the verb is implied rather than stated.

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 no explicit when-to-use, no prerequisite stating that notificationId comes from list_notifications, and no mention of the sibling preview_notification as an alternative for pre-send inspection. The agent must infer the call context entirely from the noun phrase.

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