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

The description adds several key behavioral traits beyond the readOnlyHint=true annotation. It explains the aggregation logic ('without summing overlapping groups'), the nature of the filters, and its adherence to evidentiary integrity ('Preserve nullable evidence').

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 highly dense but entirely efficient. Every clause contributes a unique operational constraint or definition, making it appropriately structured and front-loaded with core functionality.

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 complexity of the input schema and the nature of the output (metrics/comparison), the description is extremely complete, covering the data source, aggregation methodology, and filtering rules.

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?

Since schema coverage is 0%, the description carries a heavy burden. It successfully clarifies the semantic difference between how 'Domain filters' and 'keyword filters' are processed, which is vital given the nested nature of the `groups` parameter.

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 defines the tool's core function: providing 'Independent target group metrics and provider union aggregate.' It specifies that the output is an aggregate comparison, immediately distinguishing it from simple single-entity lookups.

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 provides critical context on data validity by stating the data are 'Historical provider database facts, not a live model execution.' This guidance helps the agent set expectations regarding data freshness and scope, though it doesn't explicitly list alternatives.

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