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

Annotations already declare readOnly/idempotent behavior; the description adds that the tool returns 'headline performance', 'averages', and 'trends', which gives some indication of output shape. It does not revealing more operational details (e.g., what 'headline' excludes, pagination, response size, quotas, or how dates are interpreted), so it stays at a mid level.

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?

The description is exactly two sentences with no filler. The core statement ('Get a computed campaign and audience performance …') is front-loaded, and the usage prompt appears second. It is appropriately simple and efficient.

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?

The tool has nine parameters and no output schema, but the description only covers the high-level outcome ('headline', 'averages', 'trends'). It does not communicate how to narrow the generated data (date range, campaign, send volume), what the default sort order means, or whether this is a simple return of always aggregated info. Bund on this description alone, an agent can only safely call with projectId and it will miss the available filtering capability.

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% and the description does not explain any of the 9 non-namespace parameters except a loose 'project' that maps to projectId. startDate, endDate, campaignId, search, minSendVolume, maxSendVolume, and sorting fields remain semantically undefined, exceeding the tool unusable without external knowledge.

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 states a specific action ('Get headline campaign and audience performance') and resource ('project'), with useful detail about what kind of metrics are involved (averages, trends). 'Start here' vaguely positions it as the entry point among insight siblings, but without naming them the differentiation is weaker than it could be.

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?

It gives a clear opening scenario ('Start here for 'how are we doing''), which suggests a starting point, but does not explicitly describe when to switch to sm_get_insights_advanced or sm_get_insights_expert. There is no 'when not to use' or alternative-name comparison, so guidance remains a single implied prompt rather than solid routing.

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