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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. Beyond that, the description adds real behavioral context: windows are UTC-based, each window is compared against the equivalent prior span, and the output flags whether bad bounce/complaint rates have paused campaigns and broadcasts — information not derivable from the schema.

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?

It is front-loaded with the core behavior (window plus prior-period comparison) and the long metric enumeration earns its space because there is no output schema to document returns. The single run-on sentence with chained "and" clauses is dense, but no sentence is filler.

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 needs to convey the return payload, and it does so thoroughly: metrics with rates, a daily series, top campaigns, contact count, live campaigns, sender readiness, and pause state. Only minor gaps remain, such as how project_id is obtained or whether results are paginated.

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 0%, so the description must carry parameter meaning — and it does for `days` by stating the semantics (7/30/90 UTC days) and the comparison against the previous equal span. `project_id` is left unannotated, but its meaning is self-evident from the parameter name and the tool's framing.

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 (a project's performance) and enumerates the exact metrics returned, so an agent can distinguish it from point tools like get_campaign_stats or get_broadcast_stats. The verb is implicit ("how a project is doing") rather than an explicit "get", but the scope is unambiguous.

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?

"Start here when the user asks how things are going" gives a clear entry-point rule and implicit ranking against the many narrower stats siblings. It does not explicitly say when to prefer get_campaign_stats or get_broadcast_stats for drill-down, so the routing is directional rather than exhaustive.

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