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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds no additional behavioral context such as authentication requirements, rate limits, or response format details beyond naming the metrics. It neither contradicts annotations nor enriches them, resulting in a neutral score.

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 a single, front-loaded sentence that states the action and the specific data returned. There is no fluff or redundant information; every word contributes to the meaning.

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 description covers the key return values (views, unique visitors, conversions, conversion rates) and the two required parameters are fully documented in the schema. While it doesn't mention potential nuances like time period or filtering, these are likely implied by the A/B test context. For a simple read tool with annotations covering safety, the description is nearly complete, though a note on returning aggregated historical stats would make it fully self-sufficient.

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 100%, as both app_id and test_id have descriptions in the schema. The tool description does not add any extra semantic detail about the parameters (e.g., formats, how to locate them, or relationships), so it adds no value beyond the schema. Baseline 3 applies because the schema already documents both parameters.

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 verb (Get), a clear resource (A/B test stats), and enumerates exactly which metrics are returned (views, unique visitors, conversions, conversion rates). It distinguishes itself from sibling tools like create_ab_test, update_ab_test, and list_ab_tests by focusing on stats retrieval, leaving no ambiguity about its role.

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 purpose is self-evident as a read operation for a specific A/B test, so usage is implied. However, the description does not explicitly state when to use this tool over alternatives (e.g., list_ab_tests for listing tests, get_app_analytics for broader analytics) or mention any exclusions. It relies on the agent inferring from the sibling list.

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