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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, non-mutating read operation. The description adds value by specifying the analytical scope (engagement distribution, tag and segment summaries, growth baselines, campaign consistency), which goes beyond what annotations provide. It does not mention data types, pagination, or return format, but given the annotations cover the safety profile and the description conveys the analytical intent, the behavior is transparent enough.

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 two sentences long and front-loaded with the core purpose. The first sentence lists the key analytical areas, and the second provides a conditional usage hint. There is no redundant or filler language; every word contributes to clarifying the tool's purpose. This is efficient and well-structured.

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?

Given the tool's moderate complexity (six parameters, no output schema, no nested objects), the description provides a reasonable high-level overview but lacks detail on how parameters affect the output, what data ranges are expected, or how results are presented. Since there is no output schema, the description could have explained the return value's structure, but it does not. However, the annotations indicate safety and idempotency, and the description covers the core analytical capabilities. The missing parameter semantics and return format are notable gaps, so a 3 is appropriate.

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%, meaning none of the six parameters have descriptions in the schema. The tool description does not explain any parameters either; it only describes the high-level purpose. With parameters like 'startDate', 'endDate', 'campaignId', 'minSendVolume', and 'maxSendVolume', an agent might infer their meaning from names, but 'projectId' is only marked as required without explanation, and the date format (e.g., ISO 8601) is not specified. Since the description carries the burden to compensate for schema gaps but does not, a score of 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 clearly states a specific verb ('Get') and resource ('deeper audience analytics'), and enumerates concrete content areas: engagement distribution, tag and segment summaries, growth baselines, and campaign consistency. It distinguishes itself from basic insights by noting it is for when basic insights cannot explain a change, though it does not explicitly name the basic tool in the description. The presence of sibling tools like sm_get_insights_basic and sm_get_insights_expert confirm the distinction, but the description itself only implies it.

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?

The description provides a clear usage condition: 'Use when basic insights cannot explain a change.' This orients the agent toward when to select this tool over alternatives. However, it does not explicitly state when NOT to use it, nor does it mention alternatives like sm_get_insights_expert. Given the sibling list includes both basic and expert variants, additional guidance on when to choose expert over advanced would be helpful, but the stated condition is sufficient for common use.

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