aiworkhub_prompt_bundle_ab_report

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

The description's leading 'READ-ONLY' merely restates readOnlyHint=true, so it earns no credit. What it does add beyond annotations is the 'preregistered matched' constraint, implying rows must already be paired before evaluation, but it says nothing about behavior when pairs are missing or unmatched.

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 short clause with no filler, though the leading 'READ-ONLY:' tag consumes the front-loaded position with information already present in annotations. The substantive content is packed into one dense phrase, which is efficient but borders on terse.

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?

With zero parameters, an output schema, and readOnlyHint, the structured fields cover most of the burden, so the description needn't explain returns. However, terms like 'prompt bundle' (from the name) and 'matched' are never unpacked, leaving the agent unclear on what a report over these rows actually represents.

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 tool takes zero parameters, which is the baseline-4 case. No parameter meaning needs to be conveyed, and the description correctly implies the scope is fully determined internally rather than by caller input.

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?

States a concrete verb (evaluate) and a concrete resource (preregistered matched A/B provider-usage rows), which is far more specific than a tautology. It does not differentiate from nearby read-only reporting siblings such as aiworkhub_task_usage_report or aiworkhub_cli_adapter_report_readonly, so an agent must still guess which reporting tool applies.

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?

There is no statement of when to use this tool, when not to, or which sibling to pick instead. The only scoping comes from the adjective 'preregistered', which hints at a precondition but never says who preregisters rows or what to do if none exist.

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