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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds context about what kind of analysis is returned (statistical significance, engagement velocity, geo split), which is useful but not deeply behavioral. It doesn't mention any performance implications, data freshness, or how results are computed, so it's adequate but not rich.

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, front-loads the main purpose and lists the report types concisely. The caveat that it's only for multivariate campaigns is placed at the end, which is acceptable. Every sentence contributes value with no redundancy; it's efficient but could be slightly more structured with bullet points.

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?

For a 2-parameter tool with no output schema and no nested objects, the description covers the analysis scope adequately. However, it doesn't specify the output format or any limitations (e.g., does it work only if there are multiple variants?). The annotations already cover safety, so the description is sufficient for basic use but leaves the exact return value unspecified, which is a gap given the absence of an output schema.

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 should compensate for the lack of parameter documentation. However, the description doesn't explain anything about the required parameters (projectId and campaignId) beyond what the schema states. It does not clarify the format of campaignId or whether campaignId refers to a variate campaign ID specially. Given that coverage is 0%, the description fails to add meaningful value for parameter understanding, so a 3 is generous.

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 the tool analyzes A/B campaign reports, listing specific report types (per-variant, statistical significance, engagement velocity, etc.), which distinguishes it from general campaign getters. However, it doesn't explicitly contrast with sibling tools like sm_get_insights_basic or sm_get_insights_expert that might also produce analytical reports, so it's clear but not fully differentiated.

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 notes the tool is 'Only meaningful for multivariate campaigns,' which gives a clear condition for when to use it. However, it doesn't explicitly say when not to use it or mention alternatives like sm_get_insights_* that might also handle campaign analysis. The exclusion is narrow and doesn't cover all relevant alternatives.

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