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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is established. The description adds useful context about the output content (confidence interval, lift, validation) and sliceability, but it does not disclose behavioral details like default time windows, empty-result behavior, or pagination. This adds some value beyond annotations without contradicting them.

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?

Two sentences, no filler; the core purpose and output metrics are front-loaded in the first sentence, with filtering options in the second. Every word earns its place.

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 read-only, no-required-params metrics listing, the description covers the returned values and all relevant slicing dimensions; the schema covers the parameters. The lack of an output schema is compensated by the explicit metric list, though details like the time range or the definition of 'at volume' are not specified, leaving slightly more to infer than ideal.

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?

All four parameters have schema descriptions with 100% coverage, so the schema does the heavy lifting. The description's 'Sliceable by channel, craft kind, and profile version' largely restates the schema fields, and it adds no format, enumeration, or default semantics beyond the schema's workspaceId note. Baseline 3 applies.

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 a specific resource (voice vs generic experiment) and enumerates exactly what is returned: sends, replies, acceptance counts, reply rate with 95% CI per arm, relative lift, and validation status. This clearly distinguishes it from the many other list_* siblings, which concern leads, campaigns, accounts, etc. The only minor weakness is that it starts with a noun phrase rather than an explicit verb, but the intent 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?

The description implies the tool is used when an agent needs reply-rate and lift metrics for the voice vs generic experiment, and it states the available slicing dimensions. However, it offers no explicit when-to-use vs alternatives or any exclusions (e.g., when to prefer get_campaign_metrics or list_split_optimization_logs). This is more than no guidance but less than explicit routing.

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