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

The only disclosed behavior is non-persistence of the definition; the tool does not say whether it modifies other state, whether the queue must exist, or whether evaluation has costs/limits. Annotations give readOnlyHint=false, so the description should take on more burden to clarify side effects, but it does not.

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?

A single well-formed sentence front-loads the action and immediately states the key non-persistence property. No filler or redundant restatement of the title.

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?

This is a complex tool with a nested definition schema and no output schema, but the description does not mention what the evaluation returns, how errors are surfaced, or any prerequisite such as queue existence. The non-persistence note is useful, but a significant amount of operational context is missing.

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?

The schema documents queue_id and the definition object's structure well, and the description clarifies that 'definition' is an aggregation definition. However, the description adds no meaning for queue_id or the semantics of measures/filters/dimensions beyond their names and enums.

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 verb ('Evaluate'), a resource ('an aggregation definition'), and a distinguishing scope ('against the current data without persisting it'). This clearly separates it from createQueueAggregation, getQueueAggregationResult, and refreshQueueAggregation.

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 gives a clear context: use it for a dry-run evaluation of a definition before persistence. It does not explicitly name alternatives or exclusion cases, but the non-persistence wording makes the intended scenario obvious.

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